{
  "data": {
    "a": {
      "slug": "exa-mcp",
      "name": "Exa API + MCP",
      "vendor": "Exa",
      "vendorUrl": "https://exa.ai",
      "company": "exa.ai",
      "kind": "mcp",
      "category": "search",
      "summary": "Exa's REST API over its own web index, with the official MCP server in front of it.",
      "url": "https://www.anchorterminal.com/tools/exa-mcp",
      "markdownUrl": "https://www.anchorterminal.com/tools/exa-mcp.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/exa-mcp.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/exa-mcp.json",
      "dns": "exa-mcp.grade.anchorterminal.com",
      "repo": "https://github.com/exa-labs/exa-mcp-server",
      "license": "MIT",
      "transports": [
        "stdio",
        "streamable-http",
        "http"
      ],
      "remoteUrl": "https://mcp.exa.ai/mcp",
      "packages": [
        {
          "registry": "npm",
          "name": "exa-js"
        },
        {
          "registry": "pypi",
          "name": "exa-py"
        },
        {
          "registry": "npm",
          "name": "exa-mcp-server"
        }
      ],
      "auth": "mixed",
      "authNotes": "API key as `Authorization: Bearer` or `x-api-key` header, created at dashboard.exa.ai. POST /search and /contents also accept an x402 `PAYMENT-SIGNATURE` header instead of a key. MCP server: Anonymous use with rate limits; optional API key via ?exaApiKey=, Authorization: Bearer or x-api-key header; OAuth login at https://mcp.exa.ai/mcp?login.",
      "pricing": "freemium",
      "pricingNotes": "$10 free credit a month (resets on the 1st) plus a one-time $10 sign-up bonus, no payment method required. Pay as you go per 1,000 requests, lite search $4, auto $7, deep-lite and deep $12, each with up to 10 results and $1 per 1,000 extra results. Legacy types keep their prices, instant $4, fast $7, deep-reasoning $15. Contents $1 per 1,000 pages per content type, answer $5 per 1,000, monitors $15 per 1,000. Agent API $0.012 to $1.00 a run by effort, ultra usage-based. Dynamic Highlights and the 19 October index additions at no extra charge. Enterprise volume pricing by quote (https://exa.ai/pricing).",
      "priceSummary": "$0.007 / call",
      "where": "both",
      "x402": {
        "level": "yes",
        "evidence": "Official 'Pay with x402' guide. POST /search and /contents accept x402 with USDC on Arc, Base (eip155:8453), World Chain or Solana, including Circle Gateway nanopayments, and the guide prices `lite` at $0.004 a request. An unpaid POST /search returned 402 on 2026-09-30; the guide was re-read on 2026-10-21 without a probe (https://exa.ai/docs/integrations/payments/x402/quickstart.md)",
        "endpoints": [
          {
            "url": "https://api.exa.ai/search",
            "priceUsd": 0.007,
            "network": "eip155:8453"
          },
          {
            "url": "https://api.exa.ai/contents",
            "priceUsd": 0.001,
            "network": "eip155:8453"
          }
        ]
      },
      "toolCount": 4,
      "popularity": {
        "githubStars": 4900,
        "npmWeekly": 1076635,
        "pypiWeekly": 1406207,
        "asOf": "2026-09-30"
      },
      "docsUrl": "https://exa.ai/docs",
      "llmsTxt": "https://exa.ai/docs/llms.txt",
      "openapi": "https://exa.ai/docs/exa-spec.yaml",
      "registryName": "ai.exa/exa",
      "capabilities": [
        "web.search",
        "web.fetch",
        "web.extract",
        "search.answer",
        "search.research",
        "search.news"
      ],
      "tags": [
        "official",
        "hosted",
        "local",
        "open-source",
        "x402",
        "freemium",
        "llms-txt",
        "no-card",
        "openapi",
        "python",
        "typescript",
        "enterprise",
        "webhooks",
        "mcp"
      ],
      "lastRelease": "2026-10-30",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 68.8,
        "grade": "B",
        "agentReady": false,
        "rank": 367,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 9,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 96,
          "maintenance": 88,
          "payments": 98,
          "reliability": 77,
          "schema": 86,
          "security": 43,
          "transparency": 61
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-01"
        },
        "negative": -9,
        "negativeNotes": [
          "2026-04-15. Exa's own fix (#292) says Agnost analytics on the hosted MCP captured headers, query parameters and full URLs from every request and sent them to api.agnost.ai, which leaked user API keys passed as `x-api-key` or `?exaApiKey=`. Fixed the same day, but disclosed only in the commit message, with no advisory or rotation notice that we found. Decayed for the fix, so -6 (https://github.com/exa-labs/exa-mcp-server/commit/49797a5376217da506853b12163f21db9f9c95b8)",
          "2026-10-01. The MCP server calls Agnost's `trackMCP` on startup in both the hosted and the npm stdio builds, with no README mention and no opt-out. Inputs, outputs and errors are switched off, so the events are tool names and timings. -3 (https://github.com/exa-labs/exa-mcp-server/blob/main/src/mcp-handler.ts)"
        ],
        "verdict": "x402 on /search and /contents in USDC on Arc, Base, World Chain or Solana, so an agent can pay per call with no account. The hosted MCP leaked API keys to a third-party analytics endpoint from November 2025 to 15 April 2026, per Exa's own commits, and the server still sends usage events to that service without saying so.",
        "bestFor": "Agents that search in natural language and want short highlights or page text in the same call, and for keyless or wallet-paid use.",
        "strengths": [
          "x402 on /search and /contents in USDC on Arc, Base, World Chain or Solana, so an agent can pay per call with no account",
          "Two default MCP tools for keyless use, about 1,250 characters of descriptions, and every tool marked read-only",
          "Keys can be minted by API with their own rate limit and budget",
          "Public OpenAPI, llms.txt, an error-codes page, and search warnings for request fields that have no effect",
          "$10 of credit a month with no payment method, and `lite` search at $4 per 1,000"
        ],
        "weaknesses": [
          "The hosted MCP leaked API keys to a third-party analytics endpoint from November 2025 to 15 April 2026, per Exa's own commits",
          "Agnost usage analytics in the MCP server with no disclosure or opt-out",
          "The privacy policy says query data trains Exa's models and gives no retention period",
          "No security.txt, no SECURITY.md and no prompt-injection guidance",
          "Agents API had 4 hours 56 minutes of elevated run failures on 21 to 22 September, though it read partial"
        ],
        "agentNotes": [
          "Send the key as `x-api-key` or a Bearer header, never `?exaApiKey=` in the MCP URL",
          "Ask for highlights rather than full text, and cap `maxCharacters` on `web_fetch_exa`",
          "Request only the results you'll read. More than 10 costs extra, and x402 calls stop at 10",
          "On 429, honour `Retry-After`. The QPS limit is shared by every key on the team",
          "Use `type: \"lite\"` for cheap searches, and `auto` when you need summaries, live fetches or other parameters `lite` rejects",
          "Dynamic Highlights still needs the `Exa-Beta: dynamic-highlights-2026-08-28` header per the docs, despite the GA announcement",
          "Set `budget.maxCostDollars` on `agent_run`, which a keyed MCP connection may now expose by default"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 2,
        "avgRating": 4.5,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "B",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 68.8
          }
        ],
        "editorialScores": {
          "ergonomics": 96,
          "maintenance": 88,
          "payments": 98,
          "reliability": 77,
          "schema": 86,
          "security": 43,
          "transparency": 44
        },
        "provenanceScore": 78,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-01",
            "maintenance": "2026-11-01",
            "payments": "2026-11-01",
            "reliability": "2026-11-01",
            "schema": "2026-11-01",
            "security": "2026-11-01",
            "transparency": "2026-11-01"
          },
          "last": "2026-11-01",
          "lastMoved": "2026-11-13",
          "oldest": "2026-11-01",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "http": "curl -s -X POST https://api.exa.ai/search \\\n  -H \"Authorization: Bearer $EXA_API_KEY\" -H \"Content-Type: application/json\" \\\n  -d '{\"query\":\"recent techniques for improving retrieval in RAG systems\",\"type\":\"auto\",\"contents\":{\"highlights\":true}}'",
        "claudeCode": "claude mcp add --transport http exa https://mcp.exa.ai/mcp",
        "config": {
          "mcpServers": {
            "exa": {
              "url": "https://mcp.exa.ai/mcp"
            }
          }
        },
        "x402": "curl -s https://api.exa.ai/search -H 'content-type: application/json' -d '{\"query\":\"x402 facilitators\",\"numResults\":5}' -i\n# HTTP/1.1 402 Payment Required\n# PAYMENT-REQUIRED: \u003cbase64 JSON: accepts[{scheme:\"exact\",network:\"eip155:8453\",amount:\"7000\",asset:USDC,payTo:...}]\u003e\n# retry with PAYMENT-SIGNATURE: \u003cbase64 signed authorization\u003e"
      },
      "letme": {
        "capability": "https://letme.dev/web.search",
        "tool": "https://letme.dev/exa-mcp"
      },
      "area": "web-data",
      "unitPrices": [
        {
          "item": "Search, auto",
          "unit": "1k-requests",
          "usd": 7,
          "note": "up to 10 results; legacy fast at the same price"
        },
        {
          "item": "Search, lite",
          "unit": "1k-requests",
          "usd": 4,
          "note": "up to 10 results, cached content only; legacy instant at the same price"
        },
        {
          "item": "Search, deep",
          "unit": "1k-requests",
          "usd": 12
        },
        {
          "item": "Contents",
          "unit": "1k-pages",
          "usd": 1,
          "note": "per content type"
        },
        {
          "item": "Answer",
          "unit": "1k-requests",
          "usd": 5
        }
      ],
      "provenance": {
        "legalEntity": "Exa Labs Inc.",
        "domain": "exa.ai",
        "domainRegistered": "2017-12-16",
        "endpointOnVendorDomain": true,
        "terms": "https://exa.ai/assets/Exa_Labs_Terms_of_Service.pdf",
        "privacy": "https://exa.ai/privacy-policy",
        "statusPage": "https://status.exa.ai",
        "changelog": "https://exa.ai/docs/changelog",
        "securityTxt": "none",
        "checked": "2026-11-01",
        "score": 78
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/exa-mcp.json",
      "live": {
        "slug": "exa-mcp",
        "probe": {
          "target": "https://mcp.exa.ai/mcp",
          "method": "mcp-initialize",
          "lastAt": "2026-11-18T22:43:24.171517836Z",
          "lastOk": true,
          "lastStatus": 200,
          "lastMs": 370,
          "lastNote": "initialize answered",
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 199,
          "p95ms24h": 355,
          "samples24h": 241,
          "samples30d": 7837,
          "days": [
            {
              "date": "2026-10-18",
              "probes": 256,
              "ok": 256
            },
            {
              "date": "2026-10-19",
              "probes": 255,
              "ok": 255
            },
            {
              "date": "2026-10-20",
              "probes": 252,
              "ok": 252
            },
            {
              "date": "2026-10-21",
              "probes": 253,
              "ok": 253
            },
            {
              "date": "2026-10-22",
              "probes": 253,
              "ok": 253
            },
            {
              "date": "2026-10-23",
              "probes": 248,
              "ok": 248
            },
            {
              "date": "2026-10-24",
              "probes": 251,
              "ok": 251
            },
            {
              "date": "2026-10-25",
              "probes": 250,
              "ok": 250
            },
            {
              "date": "2026-10-26",
              "probes": 252,
              "ok": 252
            },
            {
              "date": "2026-10-27",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-10-28",
              "probes": 251,
              "ok": 251
            },
            {
              "date": "2026-10-29",
              "probes": 248,
              "ok": 248
            },
            {
              "date": "2026-10-30",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-10-31",
              "probes": 251,
              "ok": 251
            },
            {
              "date": "2026-11-01",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-11-02",
              "probes": 250,
              "ok": 250
            },
            {
              "date": "2026-11-03",
              "probes": 248,
              "ok": 248
            },
            {
              "date": "2026-11-04",
              "probes": 246,
              "ok": 246
            },
            {
              "date": "2026-11-05",
              "probes": 185,
              "ok": 185
            },
            {
              "date": "2026-11-06",
              "probes": 241,
              "ok": 241
            },
            {
              "date": "2026-11-07",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-08",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-09",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-10",
              "probes": 244,
              "ok": 244
            },
            {
              "date": "2026-11-11",
              "probes": 244,
              "ok": 244
            },
            {
              "date": "2026-11-12",
              "probes": 245,
              "ok": 245
            },
            {
              "date": "2026-11-13",
              "probes": 238,
              "ok": 238
            },
            {
              "date": "2026-11-14",
              "probes": 244,
              "ok": 244
            },
            {
              "date": "2026-11-15",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-16",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-17",
              "probes": 242,
              "ok": 242
            },
            {
              "date": "2026-11-18",
              "probes": 228,
              "ok": 228
            }
          ],
          "outages": [
            {
              "start": "2026-10-04T18:58:14.45236595Z",
              "end": "2026-10-04T19:19:43.996268604Z",
              "note": "HTTP 503 server error"
            }
          ],
          "since": "2026-10-04T18:58:14.45236595Z"
        },
        "vendorStatus": {
          "page": "https://status.exa.ai",
          "indicator": "unknown",
          "summary": "no machine-readable status found",
          "checkedAt": "2026-11-18T18:52:30.80052114Z"
        },
        "versions": [
          {
            "registry": "mcp-registry",
            "name": "ai.exa/exa",
            "version": "3.4.1",
            "seenAt": "2026-11-18T22:45:57.054523297Z"
          },
          {
            "registry": "npm",
            "name": "exa-js",
            "version": "2.28.0",
            "seenAt": "2026-11-18T17:46:40.048126808Z"
          },
          {
            "registry": "npm",
            "name": "exa-mcp-server",
            "version": "3.4.3",
            "seenAt": "2026-11-18T17:46:40.954386097Z"
          },
          {
            "registry": "pypi",
            "name": "exa-py",
            "version": "2.28.0",
            "released": "2026-11-06",
            "seenAt": "2026-11-18T17:46:40.847045797Z"
          }
        ],
        "githubStars": 5241,
        "npmWeekly": 1379826,
        "pypiWeekly": 1701139,
        "securityTxt": {
          "url": "https://exa.ai/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-11-18T16:30:14.553485098Z"
        },
        "llmsTxt": {
          "url": "https://exa.ai/docs/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-11-18T16:14:17.046965539Z"
        },
        "domain": {
          "domain": "exa.ai",
          "registered": "2017-12-16",
          "source": "https://rdap.identitydigital.services/rdap/domain/exa.ai",
          "checkedAt": "2026-11-15T15:33:24.738859554Z"
        },
        "pages": [
          {
            "url": "https://exa.ai/docs/changelog",
            "kind": "deprecations",
            "status": 200,
            "checkedAt": "2026-11-18T21:43:18.669644719Z",
            "changedAt": "2026-11-15T19:42:19.064150553Z",
            "fingerprint": "8b8719cf653c"
          },
          {
            "url": "https://raw.githubusercontent.com/exa-labs/exa-js/master/CHANGELOG.md",
            "kind": "deprecations",
            "status": 304,
            "checkedAt": "2026-11-18T21:55:00.701060363Z",
            "changedAt": "2026-11-07T14:20:46.052371042Z",
            "fingerprint": "84da85c45d54"
          },
          {
            "url": "https://exa.ai/pricing",
            "kind": "pricing",
            "status": 200,
            "checkedAt": "2026-11-18T21:43:20.823245847Z",
            "changedAt": "2026-11-18T21:43:20.823245847Z",
            "fingerprint": "0a02ce479368"
          },
          {
            "url": "https://exa.ai/privacy-policy",
            "kind": "privacy",
            "status": 200,
            "checkedAt": "2026-11-18T21:43:22.936256803Z",
            "changedAt": "2026-11-17T21:02:18.262186572Z",
            "fingerprint": "b68d0ca7b2cf"
          }
        ],
        "mcpTools": {
          "url": "https://mcp.exa.ai/mcp",
          "checkedAt": "2026-11-18T04:23:40.054754208Z",
          "status": "ok",
          "protocol": "2025-11-25",
          "tools": [
            {
              "name": "web_search_exa",
              "title": "Web Search",
              "description": "Search the web for any topic and get clean, ready-to-use content.\n\n      Best for: Finding current information, news, facts, people, companies, or answering questions about any topic.\n      Returns: Clean text content from top search results.\n\n      Query tips:\n      describe the ideal page, not keywords. \"blog post comparing React and Vue performance\" not \"React vs Vue\".\n      Use category:people / category:company to search through Linkedin profiles / companies respectively.\n      If highlights are insufficient, follow up with web_fetch_exa on the best URLs.",
              "inputSchema": {
                "$schema": "http://json-schema.org/draft-07/schema#",
                "additionalProperties": false,
                "properties": {
                  "numResults": {
                    "description": "Number of search results to return (default: 10).",
                    "type": "number"
                  },
                  "objective": {
                    "description": "Goal for this search turn; say which documents should rank first, which should be excluded, and what specific facts or figures to pull from them.",
                    "maxLength": 4096,
                    "minLength": 1,
                    "type": "string"
                  },
                  "query": {
                    "description": "Natural language search query. Should be a semantically rich description of the ideal page, not just keywords. Optionally include category:\u003ctype\u003e (company, people) to focus results — e.g. 'category:people John Doe software engineer'.",
                    "minLength": 1,
                    "type": "string"
                  }
                },
                "required": [
                  "query",
                  "objective"
                ],
                "type": "object"
              },
              "annotations": {
                "destructiveHint": false,
                "idempotentHint": true,
                "openWorldHint": true,
                "readOnlyHint": true
              }
            },
            {
              "name": "web_fetch_exa",
              "title": "Fetch Web Pages",
              "description": "Read a webpage's full content as clean markdown. Use after web_search_exa when highlights are insufficient or to read any URL.\n\nBest for: Extracting full content from known URLs. Batch multiple URLs in one call.\nReturns: Clean text content and metadata from the page(s).",
              "inputSchema": {
                "$schema": "http://json-schema.org/draft-07/schema#",
                "additionalProperties": false,
                "properties": {
                  "maxCharacters": {
                    "description": "Maximum characters to extract per page (default: 3000)",
                    "minimum": 1,
                    "type": "number"
                  },
                  "urls": {
                    "description": "URLs to read. Batch multiple URLs in one call.",
                    "items": {
                      "type": "string"
                    },
                    "type": "array"
                  }
                },
                "required": [
                  "urls"
                ],
                "type": "object"
              },
              "annotations": {
                "destructiveHint": false,
                "idempotentHint": true,
                "openWorldHint": true,
                "readOnlyHint": true
              }
            }
          ],
          "schemaTokens": 605,
          "changedAt": "2026-09-28T21:55:38.894181746Z",
          "check": {
            "checker": "anchor-check/1.0",
            "totalTokens": 605,
            "counts": {
              "error": 0,
              "note": 1,
              "warn": 0
            },
            "findings": [
              {
                "rule": "TC24",
                "severity": "note",
                "message": "2 of 2 tools have no outputSchema",
                "fix": "Declare outputSchema for tools that return structured data, and return structuredContent that matches it."
              }
            ]
          }
        },
        "github": {
          "repo": "exa-labs/exa-mcp-server",
          "checkedAt": "2026-11-16T11:59:11.50883641Z",
          "stars": 5238,
          "archived": false,
          "issuesEnabled": true,
          "pushedAt": "2026-11-05T23:18:45Z",
          "openIssues": 5,
          "openPRs": 5,
          "issuesOpened90d": 26,
          "issuesClosed90d": 37,
          "prsMerged90d": 20,
          "ci": {
            "branch": "main",
            "runs": 50,
            "success": 47,
            "failure": 3,
            "other": 0,
            "latest": "success",
            "latestAt": "2026-11-03T01:15:58Z"
          },
          "replies": {
            "sampled": 25,
            "unanswered": 4,
            "medianDays": 26.6
          }
        },
        "updatedAt": "2026-11-18T22:45:57.054523297Z"
      },
      "lab": {
        "slug": "exa-mcp",
        "runs": [
          {
            "model": "qwen3.5-122b-a10b",
            "ended": "2026-11-17T23:44:28.464453414Z",
            "harness": "2026.11.17-2242",
            "status": "ok",
            "outcome": "success",
            "tools": 2,
            "toolsTried": 2,
            "toolsOk": 2,
            "toolsRefused": 0,
            "calls": 2,
            "errors": 0,
            "p50Ms": 200,
            "p95Ms": 505,
            "perTool": [
              {
                "name": "web_fetch_exa",
                "ok": true,
                "firstOk": 1,
                "calls": 1,
                "medianMs": 200
              },
              {
                "name": "web_search_exa",
                "ok": true,
                "firstOk": 1,
                "calls": 1,
                "medianMs": 505
              }
            ]
          }
        ]
      },
      "streak": {
        "days": 45,
        "from": "2026-10-04",
        "last": {
          "kind": "outage",
          "date": "2026-10-04",
          "what": "HTTP 503 server error",
          "lasted": "21 minutes"
        },
        "best": 45
      }
    },
    "answer": "Exa API + MCP and Hyperresearch score within a point of each other on agent readiness, 68.8 (B) and 68.1 (B). Hyperresearch leads on security \u0026 auth and transparency \u0026 trust.",
    "b": {
      "slug": "hyperresearch",
      "name": "Hyperresearch",
      "vendor": "Hyperresearch",
      "vendorUrl": "https://hyperresearch.ai",
      "company": "hyperresearch.ai",
      "kind": "http-api",
      "category": "search",
      "summary": "Hyperresearch is a deep research API from Thalient Labs Inc. that turns a question into a cited, checked report, with a source vault, citation verification and per-call Answers search, through REST and two remote MCP servers.",
      "url": "https://www.anchorterminal.com/tools/hyperresearch",
      "markdownUrl": "https://www.anchorterminal.com/tools/hyperresearch.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/hyperresearch.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/hyperresearch.json",
      "dns": "hyperresearch.grade.anchorterminal.com",
      "repo": "https://github.com/jordan-gibbs/hyperresearch",
      "transports": [
        "streamable-http"
      ],
      "remoteUrl": "https://answers.hyperresearch.ai/mcp",
      "packages": [
        {
          "registry": "pypi",
          "name": "hyperresearch"
        },
        {
          "registry": "pypi",
          "name": "langchain-hyperresearch"
        },
        {
          "registry": "npm",
          "name": "@hyperresearch/ai-sdk"
        },
        {
          "registry": "npm",
          "name": "@hyperresearch/langchain"
        }
      ],
      "auth": "mixed",
      "authNotes": "Self-serve scoped bearer keys (`hr_live_` billed, `hr_test_` free fixture mode) created in the console after a browser signup, with rotation, revocation and IP allowlists. MCP servers use OAuth with PKCE and a scope consent screen. A client that asks for no scopes gets read-only access.",
      "pricing": "usage",
      "pricingNotes": "Answers per call from a prepaid wallet: ask 2 cents (fast), 10 cents (standard, 20 when it digs deeper), 50 cents (max). Search 5 or 15 cents. Research runs flat: Light $9, Deep $49. $5 of Answers credit and one Light report free, no card. Top-ups from $10.",
      "priceSummary": "$0.02 / call",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in llms.txt, the pricing page, the Answers page or the docs (checked 2026-11-18). Payment is a Stripe wallet or monthly invoice.",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-18"
      },
      "docsUrl": "https://hyperresearch.ai/docs",
      "llmsTxt": "https://hyperresearch.ai/llms.txt",
      "openapi": "https://api.hyperresearch.ai/v1/openapi.json",
      "registryName": "ai.hyperresearch/answers",
      "capabilities": [
        "search.research",
        "search.answer",
        "web.search",
        "web.fetch"
      ],
      "tags": [
        "hosted",
        "remote-mcp",
        "mcp",
        "mcp-registry",
        "oauth",
        "api-key",
        "llms-txt",
        "openapi",
        "usage-priced",
        "prepaid",
        "no-card",
        "free-tier",
        "async-jobs",
        "webhooks",
        "python",
        "typescript",
        "beta",
        "no-status-page"
      ],
      "lastRelease": "2026-11-16",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 68.1,
        "grade": "B",
        "agentReady": false,
        "rank": 407,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 13,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 83,
          "maintenance": 88,
          "payments": 60,
          "reliability": 35,
          "schema": 76,
          "security": 79,
          "transparency": 71
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-18"
        },
        "negative": 0,
        "verdict": "Agents can buy one checked answer from 2 cents a call or a full research report for $9 or $49, with scoped, rotatable keys, stable error codes, idempotency keys and a six-month deprecation promise. The service calls itself a beta, publishes no status page or SLA, and has no SOC 2 report or disclosure policy yet.",
        "bestFor": "Agents that need cited, quote-checked facts or long research reports and want to keep sources in a searchable vault.",
        "strengths": [
          "Answers MCP prices are public per call: ask 2 cents (fast), 10 cents (standard), 50 cents (max), search 5 or 15 cents, with not-found calls charged less",
          "$5 of Answers credit and one free Light report on every account, no card needed. `hr_test_` keys run free fixture-mode runs",
          "Keys carry scopes (runs, vault, verify, mcp, admin), rotate with a 24-hour overlap and revoke at once. MCP uses OAuth with PKCE and a scope consent screen",
          "One error envelope with a stable `code`, `retryable` and `retry_after`, per-key rate limits by bucket, and `Idempotency-Key` on writes",
          "Fetched pages reach models inside `\u003cuntrusted-source\u003e` fences, with tool allowlists per role and private network ranges refused"
        ],
        "weaknesses": [
          "No status page, and the terms say there is no SLA and no uptime figure",
          "The terms call the service 'a beta from a young company'",
          "No SOC 2 report, no DPA on the shelf, no formal disclosure policy or bug bounty. Vulnerabilities go to the support address",
          "The research MCP server's tool schemas aren't published on a page we could read, and the OpenAPI host refused our reader",
          "Signup and MCP authorisation need a person in a browser. There is no machine payment protocol"
        ],
        "agentNotes": [
          "Use Answers (`data_and_web_answer` with mode `auto`) for one fact, and start a Light or Deep run only when the user wants a written report",
          "Send an `Idempotency-Key` on every write and reuse it only with an unchanged body, so a retried run or answer is charged once",
          "Poll a run with `GET /v1/runs/{id}` about once a minute, or stream its events. A Light run takes about 30 to 40 minutes",
          "If a response has `retryable: false`, change the request rather than retrying. Branch on `error.code`, never on the message",
          "Use a key that starts `hr_test_` to build and test an integration without spending"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "B",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 68.1
          }
        ],
        "editorialScores": {
          "ergonomics": 83,
          "maintenance": 88,
          "payments": 60,
          "reliability": 35,
          "schema": 76,
          "security": 79,
          "transparency": 84
        },
        "provenanceScore": 58,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-18",
            "maintenance": "2026-11-18",
            "payments": "2026-11-18",
            "reliability": "2026-11-18",
            "schema": "2026-11-18",
            "security": "2026-11-18",
            "transparency": "2026-11-18"
          },
          "last": "2026-11-18",
          "oldest": "2026-11-18",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "http": "curl -X POST https://api.hyperresearch.ai/v1/answers -H \"Authorization: Bearer $HYPERRESEARCH_KEY\" -H \"Idempotency-Key: $(uuidgen)\" -H 'Content-Type: application/json' -d '{\"question\":\"How old must a US senator be?\",\"mode\":\"fast\"}'",
        "claudeCode": "claude mcp add hyperresearch-answers --transport http https://answers.hyperresearch.ai/mcp",
        "config": {
          "mcpServers": {
            "hyperresearch": {
              "url": "https://mcp.hyperresearch.ai/mcp"
            },
            "hyperresearch-answers": {
              "url": "https://answers.hyperresearch.ai/mcp"
            }
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/search.research",
        "tool": "https://letme.dev/hyperresearch"
      },
      "area": "web-data",
      "unitPrices": [
        {
          "item": "Answers ask, fast",
          "unit": "call",
          "usd": 0.02,
          "note": "1 to 2 cents if not found"
        },
        {
          "item": "Answers ask, standard",
          "unit": "call",
          "usd": 0.1,
          "note": "20 cents when it digs deeper"
        },
        {
          "item": "Answers ask, max",
          "unit": "call",
          "usd": 0.5,
          "note": "10 to 50 cents if not found"
        },
        {
          "item": "Answers search, standard",
          "unit": "call",
          "usd": 0.05
        },
        {
          "item": "Answers search, max",
          "unit": "call",
          "usd": 0.15
        },
        {
          "item": "Light research run",
          "unit": "tx",
          "usd": 9,
          "note": "one report"
        },
        {
          "item": "Deep research run",
          "unit": "tx",
          "usd": 49,
          "note": "one report"
        }
      ],
      "provenance": {
        "legalEntity": "Thalient Labs Inc.",
        "domain": "hyperresearch.ai",
        "domainRegistered": "",
        "endpointOnVendorDomain": true,
        "terms": "https://hyperresearch.ai/legal/terms",
        "privacy": "https://hyperresearch.ai/legal/privacy",
        "statusPage": "",
        "changelog": "",
        "securityTxt": "none",
        "checked": "2026-11-18",
        "notes": [
          "The about page names Thalient Labs Inc., a Delaware corporation incorporated on 16 March 2026, at 1001 S. Main St., Suite 500, Kalispell, MT 59901, and says the terms, privacy policy and Stripe receipts carry the same details. The terms choose Delaware law and have no arbitration clause.",
          "Terms version 1.7, effective 23 September 2026, last updated 4 October 2026. Privacy policy version 1.7, effective 17 September 2026, per the about page.",
          "hyperresearch.ai/robots.txt allows ClaudeBot, anthropic-ai and Claude-Web and disallows /api/, with Content-Signal search=yes, ai-input=yes, ai-train=yes. mcp. and answers.hyperresearch.ai publish comment-only robots files with no rules. api.hyperresearch.ai's robots.txt asked for a sign-in, so that host wasn't read.",
          "/.well-known/security.txt answers 404. No status page found.",
          "The about page asks directories to copy its product descriptions verbatim. We wrote our own."
        ],
        "score": 58
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/hyperresearch.json",
      "live": {
        "slug": "hyperresearch",
        "probe": {
          "target": "https://answers.hyperresearch.ai/mcp",
          "method": "get",
          "lastAt": "2026-11-18T22:43:33.50023008Z",
          "lastOk": true,
          "lastStatus": 406,
          "lastMs": 233,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 328,
          "p95ms24h": 813,
          "samples24h": 11,
          "samples30d": 11,
          "days": [
            {
              "date": "2026-11-18",
              "probes": 11,
              "ok": 11
            }
          ],
          "since": "2026-11-18T21:38:05.612316973Z"
        },
        "versions": [
          {
            "registry": "mcp-registry",
            "name": "ai.hyperresearch/answers",
            "version": "1.0.1",
            "seenAt": "2026-11-18T22:45:57.054523297Z"
          }
        ],
        "mcpTools": {
          "url": "https://mcp.hyperresearch.ai/mcp",
          "checkedAt": "2026-10-01T21:59:49.591132636Z",
          "status": "auth",
          "note": "asks for credentials before listing its tools",
          "changedAt": "2026-10-01T21:59:49.591132636Z"
        },
        "updatedAt": "2026-11-18T22:45:57.054523297Z"
      },
      "streak": {
        "days": 0,
        "from": "2026-11-18",
        "sinceWatching": true,
        "best": 0
      }
    },
    "edges": [
      {
        "by": 42,
        "category": "reliability",
        "leads": "exa-mcp",
        "name": "Reliability",
        "reasons": {
          "a": "Instatus page at status.exa.ai with Search API, Exa MCP, Agents API and Websets components and dated history (20). In the 90 days to 1 November, history/1 shows the Search API's 1-minute blip (16 September), a 1 hour 24 minute latency incident (18 September) and 2 hours 21 minutes of elevated latency with some failed requests (21 September), and the Agents API's 25 minutes of runs failing to start (18 September, labelled major) and 4 hours 56 minutes in which 'some agent runs may fail to start or complete' (21 to 22 September). August is per the 21 October check, not re-read on 1 November (history/2 answers 404 again), with a 10-minute Search API major outage on 14 August and a 53-minute latency incident. No notices in October or November. By this run's reading each hit one product or a subset of requests and none was an hour of a core API down, so all are minor (20, up from 10, where the 21 to 22 September Agents API incident had been counted as a major). Rate limits published per endpoint, 10 QPS search and answer, 5 QPS deep, 100 QPS contents, 5 QPS and 50 active Agent runs (15). 429 with `Retry-After` when available and exponential backoff advice. We found no idempotency guidance for creating Agent runs, which cost money (12). No SLA found. The pricing page lists \"Enterprise SLAs\" on the contract plan, with no terms published (0). Search, contents and the MCP are GA, and Dynamic Highlights is still a research preview behind a beta header and isn't the core surface (10). 20 + 20 + 15 + 12 + 0 + 10 = 77.",
          "b": "Graded on the hosted API and the two remote MCP servers. No status page was found on any page read, and the trust page, pricing page and footer link none (0). No readable incident history (5). Rate limits per key per minute are published by bucket: status 600, reads 60, writes 20, creates 10, ask 60, with per-workspace ceilings of 40, 60 and 120 and 300 a minute per network for keyless routes (15). 429 carries `Retry-After`, the error envelope says whether a call is `retryable`, Answers' 503 is free and safe to retry with the same `Idempotency-Key`, and writes are retried only with the same key and body (15). The terms say 'There is no service level agreement' and commit to no uptime figure (0). The terms call the service 'a beta from a young company' (0). 0+5+15+15+0+0 = 35."
        },
        "scores": {
          "a": 77,
          "b": 35
        }
      },
      {
        "by": 38,
        "category": "payments",
        "leads": "exa-mcp",
        "name": "Payments \u0026 pricing",
        "reasons": {
          "a": "x402 on POST /search and /contents, USDC on Arc, Base, World Chain or Solana, including Circle Gateway nanopayments, not on answer, Agent runs, monitors or Websets, so partial (30). Per-call prices published without login, $0.004 for `lite` (and legacy `instant`) to $0.015 for legacy deep-reasoning per search (20). $10 a month and a $10 onboarding bonus, and the pricing page now states \"No payment method required\" (20). An agent can pay by x402 with no account, and the hosted MCP works anonymously within rate limits (20). Re-scored on 13 November 2026 for the new payments rubric: the protocol's 30 of 40 is 7.5 of 10, and the other lines' 60 is 90 at 30 each, so 90 is 98.",
          "b": "No x402, MPP or L402 (0). Per-call prices for Answers and flat per-run prices (Light $9, Deep $49) are published without login, with rerun discounts and refund rules (30). $5 of Answers credit and the first Light report free on every account, no card needed, and `hr_test_` keys are never billed (30). A person signs up through Clerk in a browser and creates keys in the console, and MCP clients authorise in a browser (0). 0+30+30+0 = 60."
        },
        "scores": {
          "a": 98,
          "b": 60
        }
      },
      {
        "by": 36,
        "category": "security",
        "leads": "hyperresearch",
        "name": "Security \u0026 auth",
        "reasons": {
          "a": "Bearer or `x-api-key` keys, and a team-management API creates keys with their own rate limit and budget. The hosted MCP also takes OAuth. The README documents `?exaApiKey=` in the URL, so 25 less 10 (15). Every tool is read-only and annotated so, and `?tools=` limits the set. Agent runs spend credit but change nothing. Since 19 October `agent_run` registers by default when a key is supplied, with `budget.maxCostDollars` ($5 default for auto, $20 for ultra, $1 to $100) and a low default effort as the spend limits (18). Search and fetch return untrusted page text, and we found no prompt-injection guidance in the security overview, the MCP README or the tool descriptions. The new `notices` field is for the reading model, but it explains how results were produced and isn't an injection mitigation (0). No audit log found (0). SOC 2 Type II with reports in a trust centre. No security.txt (404 on 21 October), no SECURITY.md, no bug bounty and no GitHub advisories. The April 2026 key leak below was handled in a commit message only (10).",
          "b": "Bearer keys of 32 random bytes stored as salted hashes, shown once, scoped to `runs:read`, `runs:write`, `vault:read`, `vault:write`, `verify`, `mcp` and `admin`, with a last-used time, rotation with a 24-hour overlap and instant revocation, plus an IP allowlist. MCP uses OAuth with PKCE and a consent screen that lists each scope. The docs say never to put keys in URLs (30). A client that requests no scopes gets read-only access, billed scopes are marked on the consent screen, and every workspace has a spend cap. No confirmation step for deletes was found (16 of 20). The trust page documents `\u003cuntrusted-source\u003e` fences on every fetched body, forged fence tags neutralised, per-role tool allowlists, schema-validated arguments and private address ranges refused (15). A workspace audit log exportable as NDJSON, a 365-day default window, and a list of agent connections that can be revoked (15). No security.txt (404), no formal disclosure policy and no bug bounty, and the trust page says there is no SOC 2 report. Vulnerabilities go to support@hyperresearch.ai (3 of 20). 30+16+15+15+3 = 79."
        },
        "scores": {
          "a": 43,
          "b": 79
        }
      },
      {
        "by": 13,
        "category": "ergonomics",
        "leads": "exa-mcp",
        "name": "Agent ergonomics",
        "reasons": {
          "a": "On a keyless connection two tools are on by default, `web_search_exa` and `web_fetch_exa`, about 1,250 characters of descriptions between them. Since the 19 October commit on main, `agent_run` (about 500 characters plus a larger input schema) is also on by default when the user supplies a key, though the README still lists it as optional. `?tools=` turns on `web_search_advanced_exa` and picks the set (25). `numResults`, `maxCharacters`, highlights instead of full text, category, domain and date filters, and in `web_search_advanced_exa` the `lite` type (20). The error-codes page lists codes, and the MCP server rewrites a 429 into a message about the free tier and keys and now passes search notices to the model. Errors reach the model as text rather than a code (16). Every tool sets `readOnlyHint`, `destructiveHint: false` and `idempotentHint` (false on `agent_run`), and the server retries transient errors twice (20). Only `query` is required. Python and TypeScript SDKs (15).",
          "b": "Answers is three compact tools (`data_and_web_answer`, `data_and_web_search` and the free `get_pending_answer`), and an answer returns only a short answer, its quotes and links. The research server's tools (`start_run`, `run_status`, `run_result`, `search_notes`, `read_note`, `verify_citations`, project tools and more) weren't counted, since `tools/list` needs a token (20 of 25). `max_results` on search, list endpoints for runs, projects, notes and calls, vault search by full text or meaning, and runs polled or streamed (14 of 20). Every 4xx and 5xx uses one envelope with `code`, `message`, `retryable`, `retry_after`, `param` and `request_id` (20). `Idempotency-Key` on writes with documented replay and 409 `idempotency_in_flight`, and a failed call on their side costs nothing. MCP tool annotations weren't readable (14 of 20). Only a query and a tier are required to start a run. Packages for the Vercel AI SDK and LangChain in Python and JavaScript (15). 20+14+20+14+15 = 83."
        },
        "scores": {
          "a": 96,
          "b": 83
        }
      },
      {
        "by": 10,
        "category": "schema",
        "leads": "exa-mcp",
        "name": "Schema \u0026 documentation",
        "reasons": {
          "a": "OpenAPI at exa.ai/docs/exa-spec.yaml, re-read on 21 October with the new `lite` type, its accepted parameters and the `warnings` and `notices` response fields, and JSON Schema inputs on every MCP tool (25). llms.txt and Markdown docs (10). `web_search_exa` tells the model how to phrase a query and when to follow up with `web_fetch_exa`, and deprecated tools name their replacement. The `agent_run` description on the main branch since 19 October says it isn't for a single lookup or a known URL and names the sibling tools, but that commit isn't in npm 3.4.2 and we couldn't confirm the hosted server runs it, so the line stays where it was. Nothing else says when not to use a tool (15). Inputs coerce loosely. `numResults` is described as 1 to 100 but the schema has no bounds, and bad numbers fall back to defaults silently. On the API, `lite` rejects an unsupported parameter with a 400 that names it, and ignored fields such as `startCrawlDate` now come back as `IGNORED_FIELD` warnings (10). An error-codes page and examples on every endpoint page (13). Dated changelog with deprecations, the latest entry 19 October. The MCP repository has no tags, so versions show only in package.json and the registry (13).",
          "b": "llms.txt and the versioning page name an OpenAPI 3.1 document at api.hyperresearch.ai/v1/openapi.json, and the API reference has one page per operation generated from it. api.hyperresearch.ai's robots.txt asked for a sign-in, so read.py closed the host and the file wasn't read (20 of 25). llms.txt, and every docs page as Markdown with `.md` (10). The Answers page says when to use fast, standard, max or auto and that fast skips structured sources, and the docs say Answers is for one fact and runs for a report. The research MCP server's tool descriptions couldn't be read (12 of 20). Modes and run tiers are enums, and examples show `max_results`, but the schemas themselves weren't read (10 of 15). Request and result examples, one error envelope with status meanings and a stable `code` (14 of 15). The version is in the path (/v1) with an additive-only promise, but the hosted service has no public changelog. The open-source CLI's CHANGELOG.md is dated (10 of 15). 20+10+12+10+14+10 = 76."
        },
        "scores": {
          "a": 86,
          "b": 76
        }
      },
      {
        "by": 10,
        "category": "transparency",
        "leads": "hyperresearch",
        "name": "Transparency \u0026 trust",
        "reasons": {
          "a": "The MCP server is MIT and the API is closed with published terms (20). The privacy policy, still dated 29 June 2026 on 21 October, says query data is used to train and fine-tune Exa's models and states no retention period. Zero data retention needs a sales conversation, and the DPA sits in the trust centre (12). Dated deprecations in the changelog, such as the `pdf`, `github` and `tweet` categories on 23 July and the `instant`, `fast` and `deep-reasoning` search types made legacy on 19 October, with no removal dates (12). The MCP server, hosted and on npm, sends usage events to Agnost (api.agnost.ai) with no mention in the README, no opt-out flag, and no named subprocessor list in the privacy policy, unchanged on main on 21 October (0).",
          "b": "The hosted service is closed with terms from Thalient Labs Inc. (version 1.7), and the CLI that runs the same pipeline is MIT (20 of 30). The trust page states retention per record type (content kept until deleted, verification inputs 7 days, billing at least 7 years, audit log 365 days by default), names the known gaps (the run index and questions are kept indefinitely, no automatic expiry), says customer content isn't used for training, and says it matches the privacy policy. No DPA on the shelf (26 of 30). A written deprecation policy: at least six months' notice, `Deprecation` and `Sunset` headers and a list of deprecations, plus 30 days' notice by email before a shutdown (20). Subprocessors are listed with what each receives and their countries, and the trust page says there is no data residency guarantee on Cloudflare's network (18 of 20). 20+26+20+18 = 84."
        },
        "scores": {
          "a": 61,
          "b": 71
        }
      }
    ],
    "facts": [
      {
        "a": "MCP server",
        "b": "HTTP API",
        "name": "Kind"
      },
      {
        "a": "Exa",
        "b": "Hyperresearch",
        "name": "Vendor"
      },
      {
        "a": "https://mcp.exa.ai/mcp",
        "b": "https://answers.hyperresearch.ai/mcp",
        "name": "Hosted endpoint"
      },
      {
        "a": "stdio, Streamable HTTP, HTTP",
        "b": "Streamable HTTP",
        "name": "Transports"
      },
      {
        "a": "OAuth or key",
        "b": "OAuth or key",
        "name": "Auth"
      },
      {
        "a": "Freemium",
        "b": "Pay per use",
        "name": "Pricing"
      },
      {
        "a": "$4 per 1,000 requests",
        "b": "$0.05 per call",
        "name": "Price for web search"
      },
      {
        "a": "yes, from $0.007/call",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "MIT",
        "b": "none",
        "name": "Licence"
      },
      {
        "a": "4",
        "b": "none",
        "name": "Tools exposed"
      },
      {
        "a": "yes",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "ai.exa/exa",
        "b": "ai.hyperresearch/answers",
        "name": "MCP registry"
      },
      {
        "a": "2026-10-30",
        "b": "2026-11-16",
        "name": "Last release"
      },
      {
        "a": "not read yet",
        "b": "2026-11-17",
        "name": "Terms last updated"
      },
      {
        "a": "2026-06-29",
        "b": "2026-11-17",
        "name": "Privacy policy last updated"
      },
      {
        "a": "yes",
        "b": "not found in the text",
        "name": "Customer content may train models"
      },
      {
        "a": "not read yet",
        "b": "not found in the text",
        "name": "Terms restrict automated access"
      },
      {
        "a": "not read yet",
        "b": "yes",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "not read yet",
        "b": "not found in the text",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "not read yet",
        "b": "not found in the text",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "4.9k stars, 1.1M npm/wk, 1.4M PyPI/wk",
        "b": "none",
        "name": "Popularity"
      },
      {
        "a": "4.5/5 (2)",
        "b": "none",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "Exa API + MCP and Hyperresearch score within a point of each other on agent readiness, 68.8 (B) and 68.1 (B). Hyperresearch leads on security \u0026 auth and transparency \u0026 trust.",
        "question": "Which is better for AI agents, Exa API + MCP or Hyperresearch?"
      },
      {
        "answer": "Both take an API key or an OAuth sign-in. An agent can also pay Exa API + MCP per call over x402, with no account.",
        "question": "Do Exa API + MCP and Hyperresearch need an API key?"
      },
      {
        "answer": "Yes. Exa API + MCP has a hosted endpoint at https://mcp.exa.ai/mcp and Hyperresearch at https://answers.hyperresearch.ai/mcp.",
        "question": "Can an agent call Exa API + MCP and Hyperresearch without installing anything?"
      },
      {
        "answer": "Exa API + MCP is open source (MIT). No open-source release is listed for Hyperresearch.",
        "question": "Are Exa API + MCP and Hyperresearch open source?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 77 against 35",
          "Schema \u0026 documentation, 86 against 76",
          "Agent ergonomics, 96 against 83",
          "Payments \u0026 pricing, 98 against 60"
        ],
        "also": [
          "An agent can pay per call over x402, with no account",
          "Runs on your own machine",
          "Open source"
        ],
        "goodFor": "Agents that search in natural language and want short highlights or page text in the same call, and for keyless or wallet-paid use.",
        "slug": "exa-mcp",
        "watchFor": "The hosted MCP leaked API keys to a third-party analytics endpoint from November 2025 to 15 April 2026, per Exa's own commits"
      },
      {
        "aheadOn": [
          "Security \u0026 auth, 79 against 43",
          "Transparency \u0026 trust, 71 against 61"
        ],
        "also": [
          "No incidents deducted, where Exa API + MCP loses 9 points for them"
        ],
        "goodFor": "Agents that need cited, quote-checked facts or long research reports and want to keep sources in a searchable vault.",
        "slug": "hyperresearch",
        "watchFor": "No status page, and the terms say there is no SLA and no uptime figure"
      }
    ],
    "history": {
      "exa-mcp": [
        {
          "causes": [
            "method"
          ],
          "date": "2026-11-13",
          "delta": 1,
          "from": 67.8,
          "fromGrade": "B",
          "to": 68.8,
          "toGrade": "B"
        },
        {
          "causes": [
            "correction"
          ],
          "date": "2026-11-01",
          "delta": 2,
          "from": 65.8,
          "fromGrade": "B",
          "to": 67.8,
          "toGrade": "B"
        },
        {
          "causes": [
            "method"
          ],
          "date": "2026-10-30",
          "delta": -0.3,
          "from": 66.1,
          "fromGrade": "B",
          "to": 65.8,
          "toGrade": "B"
        }
      ],
      "hyperresearch": null
    },
    "job": {
      "capability": "web.search",
      "name": "Web search"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-exa-mcp.json",
        "title": "Web Search Tool on Amazon Bedrock AgentCore vs Exa API + MCP",
        "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-exa-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-hyperresearch.json",
        "title": "Web Search Tool on Amazon Bedrock AgentCore vs Hyperresearch",
        "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-hyperresearch"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-exa-mcp.json",
        "title": "Grounding with Bing Search vs Exa API + MCP",
        "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-exa-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-hyperresearch.json",
        "title": "Grounding with Bing Search vs Hyperresearch",
        "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-hyperresearch"
      },
      {
        "json": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-exa-mcp.json",
        "title": "Brave Search API + MCP vs Exa API + MCP",
        "url": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-exa-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-hyperresearch.json",
        "title": "Brave Search API + MCP vs Hyperresearch",
        "url": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-hyperresearch"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-exa-mcp.json",
        "title": "Cloudflare Web Search API vs Exa API + MCP",
        "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-exa-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-hyperresearch.json",
        "title": "Cloudflare Web Search API vs Hyperresearch",
        "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-hyperresearch"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-exa-mcp.json",
        "title": "DeepSeek Search and Fetch API vs Exa API + MCP",
        "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-exa-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-hyperresearch.json",
        "title": "DeepSeek Search and Fetch API vs Hyperresearch",
        "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-hyperresearch"
      },
      {
        "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-firecrawl-mcp.json",
        "title": "Exa API + MCP vs Firecrawl MCP",
        "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-firecrawl-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-kagi-search.json",
        "title": "Exa API + MCP vs Kagi Search API",
        "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-kagi-search"
      },
      {
        "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-linkup.json",
        "title": "Exa API + MCP vs Linkup",
        "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-linkup"
      },
      {
        "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-mojeek.json",
        "title": "Exa API + MCP vs Mojeek Web Search API",
        "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-mojeek"
      },
      {
        "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-newscatcher.json",
        "title": "Exa API + MCP vs NewsCatcher",
        "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-newscatcher"
      },
      {
        "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-parallel-search-api.json",
        "title": "Exa API + MCP vs Parallel Search and Task APIs",
        "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-parallel-search-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-perplexity-search-api.json",
        "title": "Exa API + MCP vs Perplexity Search API",
        "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-perplexity-search-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-searchapi-io.json",
        "title": "Exa API + MCP vs SearchAPI.io",
        "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-searchapi-io"
      },
      {
        "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-serpapi.json",
        "title": "Exa API + MCP vs SerpApi",
        "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-serpapi"
      },
      {
        "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-serper.json",
        "title": "Exa API + MCP vs Serper",
        "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-serper"
      },
      {
        "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-serphouse.json",
        "title": "Exa API + MCP vs SERPHouse",
        "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-serphouse"
      },
      {
        "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-serpkite.json",
        "title": "Exa API + MCP vs SerpKite",
        "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-serpkite"
      },
      {
        "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-specstream.json",
        "title": "Exa API + MCP vs SpecStream",
        "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-specstream"
      },
      {
        "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-tavily-mcp.json",
        "title": "Exa API + MCP vs Tavily API + MCP",
        "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-tavily-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-tinyfish-search.json",
        "title": "Exa API + MCP vs TinyFish Search",
        "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-tinyfish-search"
      },
      {
        "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-valyu.json",
        "title": "Exa API + MCP vs Valyu",
        "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-valyu"
      },
      {
        "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-you-com-api.json",
        "title": "Exa API + MCP vs You.com APIs",
        "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-you-com-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-hyperresearch.json",
        "title": "Firecrawl MCP vs Hyperresearch",
        "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-hyperresearch"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hyperresearch-vs-kagi-search.json",
        "title": "Hyperresearch vs Kagi Search API",
        "url": "https://www.anchorterminal.com/compare/hyperresearch-vs-kagi-search"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hyperresearch-vs-mojeek.json",
        "title": "Hyperresearch vs Mojeek Web Search API",
        "url": "https://www.anchorterminal.com/compare/hyperresearch-vs-mojeek"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hyperresearch-vs-searchapi-io.json",
        "title": "Hyperresearch vs SearchAPI.io",
        "url": "https://www.anchorterminal.com/compare/hyperresearch-vs-searchapi-io"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hyperresearch-vs-serpapi.json",
        "title": "Hyperresearch vs SerpApi",
        "url": "https://www.anchorterminal.com/compare/hyperresearch-vs-serpapi"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hyperresearch-vs-serper.json",
        "title": "Hyperresearch vs Serper",
        "url": "https://www.anchorterminal.com/compare/hyperresearch-vs-serper"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hyperresearch-vs-serphouse.json",
        "title": "Hyperresearch vs SERPHouse",
        "url": "https://www.anchorterminal.com/compare/hyperresearch-vs-serphouse"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hyperresearch-vs-serpkite.json",
        "title": "Hyperresearch vs SerpKite",
        "url": "https://www.anchorterminal.com/compare/hyperresearch-vs-serpkite"
      },
      {
        "json": "https://www.anchorterminal.com/compare/arcmira-vs-exa-mcp.json",
        "title": "Arcmira vs Exa API + MCP",
        "url": "https://www.anchorterminal.com/compare/arcmira-vs-exa-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/arcmira-vs-hyperresearch.json",
        "title": "Arcmira vs Hyperresearch",
        "url": "https://www.anchorterminal.com/compare/arcmira-vs-hyperresearch"
      },
      {
        "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-grep-ai.json",
        "title": "Exa API + MCP vs Grep AI",
        "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-grep-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-liner-mcp.json",
        "title": "Exa API + MCP vs Liner Search MCP",
        "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-liner-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/grep-ai-vs-hyperresearch.json",
        "title": "Grep AI vs Hyperresearch",
        "url": "https://www.anchorterminal.com/compare/grep-ai-vs-hyperresearch"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hyperresearch-vs-liner-mcp.json",
        "title": "Hyperresearch vs Liner Search MCP",
        "url": "https://www.anchorterminal.com/compare/hyperresearch-vs-liner-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hyperresearch-vs-linkup.json",
        "title": "Hyperresearch vs Linkup",
        "url": "https://www.anchorterminal.com/compare/hyperresearch-vs-linkup"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hyperresearch-vs-newscatcher.json",
        "title": "Hyperresearch vs NewsCatcher",
        "url": "https://www.anchorterminal.com/compare/hyperresearch-vs-newscatcher"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hyperresearch-vs-parallel-search-api.json",
        "title": "Hyperresearch vs Parallel Search and Task APIs",
        "url": "https://www.anchorterminal.com/compare/hyperresearch-vs-parallel-search-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hyperresearch-vs-perplexity-search-api.json",
        "title": "Hyperresearch vs Perplexity Search API",
        "url": "https://www.anchorterminal.com/compare/hyperresearch-vs-perplexity-search-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hyperresearch-vs-specstream.json",
        "title": "Hyperresearch vs SpecStream",
        "url": "https://www.anchorterminal.com/compare/hyperresearch-vs-specstream"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hyperresearch-vs-tavily-mcp.json",
        "title": "Hyperresearch vs Tavily API + MCP",
        "url": "https://www.anchorterminal.com/compare/hyperresearch-vs-tavily-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hyperresearch-vs-tinyfish-search.json",
        "title": "Hyperresearch vs TinyFish Search",
        "url": "https://www.anchorterminal.com/compare/hyperresearch-vs-tinyfish-search"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hyperresearch-vs-valyu.json",
        "title": "Hyperresearch vs Valyu",
        "url": "https://www.anchorterminal.com/compare/hyperresearch-vs-valyu"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hyperresearch-vs-you-com-api.json",
        "title": "Hyperresearch vs You.com APIs",
        "url": "https://www.anchorterminal.com/compare/hyperresearch-vs-you-com-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-fetch-reference-server.json",
        "title": "Exa API + MCP vs Fetch (MCP reference server)",
        "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-fetch-reference-server"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-hyperresearch.json",
        "title": "Fetch (MCP reference server) vs Hyperresearch",
        "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-hyperresearch"
      }
    ],
    "panel": null,
    "scores": [
      {
        "by": 42,
        "edge": "exa-mcp",
        "exa-mcp": 77,
        "hyperresearch": 35,
        "key": "reliability",
        "name": "Reliability",
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 10,
        "edge": "exa-mcp",
        "exa-mcp": 86,
        "hyperresearch": 76,
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "weight": 13
      },
      {
        "by": 13,
        "edge": "exa-mcp",
        "exa-mcp": 96,
        "hyperresearch": 83,
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "weight": 13
      },
      {
        "by": 36,
        "edge": "hyperresearch",
        "exa-mcp": 43,
        "hyperresearch": 79,
        "key": "security",
        "name": "Security \u0026 auth",
        "weight": 14
      },
      {
        "by": 38,
        "edge": "exa-mcp",
        "exa-mcp": 98,
        "hyperresearch": 60,
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 0,
        "edge": "",
        "exa-mcp": 88,
        "hyperresearch": 88,
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "weight": 7
      },
      {
        "by": 10,
        "edge": "hyperresearch",
        "exa-mcp": 61,
        "hyperresearch": 71,
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "weight": 7
      }
    ],
    "summary": "Exa API + MCP and Hyperresearch score within a point of each other on agent readiness, 68.8 (B) and 68.1 (B). Hyperresearch leads on security \u0026 auth and transparency \u0026 trust. Both do web search. Exa API + MCP accepts x402. Hyperresearch doesn't.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "exa-mcp": "x402 on /search and /contents in USDC on Arc, Base, World Chain or Solana, so an agent can pay per call with no account. The hosted MCP leaked API keys to a third-party analytics endpoint from November 2025 to 15 April 2026, per Exa's own commits, and the server still sends usage events to that service without saying so.",
      "hyperresearch": "Agents can buy one checked answer from 2 cents a call or a full research report for $9 or $49, with scoped, rotatable keys, stable error codes, idempotency keys and a six-month deprecation promise. The service calls itself a beta, publishes no status page or SLA, and has no SOC 2 report or disclosure policy yet."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/exa-mcp-vs-hyperresearch",
    "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-hyperresearch.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/exa-mcp-vs-hyperresearch.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/exa-mcp-vs-hyperresearch.min.md"
  },
  "markdown": "Exa API + MCP and Hyperresearch score within a point of each other on agent readiness, 68.8 (B) and 68.1 (B). Hyperresearch leads on security \u0026 auth and transparency \u0026 trust. Both do web search. Exa API + MCP accepts x402. Hyperresearch doesn't.\n\n- Exa API + MCP: grade B, 68.8/100, rank #367 of 1557. Markdown https://www.anchorterminal.com/tools/exa-mcp.md · JSON https://www.anchorterminal.com/api/v1/tools/exa-mcp.json\n- Hyperresearch: grade B, 68.1/100, rank #407 of 1557. Markdown https://www.anchorterminal.com/tools/hyperresearch.md · JSON https://www.anchorterminal.com/api/v1/tools/hyperresearch.json\n- Best web search APIs for AI agents: https://www.anchorterminal.com/best/search/index.md\n- All 353 search comparisons: https://www.anchorterminal.com/compare/search/index.md\n\n## Which one, for what\n\n### Exa API + MCP (B)\n\nGood for: Agents that search in natural language and want short highlights or page text in the same call, and for keyless or wallet-paid use.\n\nAhead on:\n- Reliability, 77 against 35\n- Schema \u0026 documentation, 86 against 76\n- Agent ergonomics, 96 against 83\n- Payments \u0026 pricing, 98 against 60\n\nAlso in its favour:\n- An agent can pay per call over x402, with no account\n- Runs on your own machine\n- Open source\n\nWatch for: The hosted MCP leaked API keys to a third-party analytics endpoint from November 2025 to 15 April 2026, per Exa's own commits\n\n### Hyperresearch (B)\n\nGood for: Agents that need cited, quote-checked facts or long research reports and want to keep sources in a searchable vault.\n\nAhead on:\n- Security \u0026 auth, 79 against 43\n- Transparency \u0026 trust, 71 against 61\n\nAlso in its favour:\n- No incidents deducted, where Exa API + MCP loses 9 points for them\n\nWatch for: No status page, and the terms say there is no SLA and no uptime figure\n\n\n## Why the edge\n\n### Reliability: Exa API + MCP +42\n\n- Exa API + MCP (77): Instatus page at status.exa.ai with Search API, Exa MCP, Agents API and Websets components and dated history (20). In the 90 days to 1 November, history/1 shows the Search API's 1-minute blip (16 September), a 1 hour 24 minute latency incident (18 September) and 2 hours 21 minutes of elevated latency with some failed requests (21 September), and the Agents API's 25 minutes of runs failing to start (18 September, labelled major) and 4 hours 56 minutes in which 'some agent runs may fail to start or complete' (21 to 22 September). August is per the 21 October check, not re-read on 1 November (history/2 answers 404 again), with a 10-minute Search API major outage on 14 August and a 53-minute latency incident. No notices in October or November. By this run's reading each hit one product or a subset of requests and none was an hour of a core API down, so all are minor (20, up from 10, where the 21 to 22 September Agents API incident had been counted as a major). Rate limits published per endpoint, 10 QPS search and answer, 5 QPS deep, 100 QPS contents, 5 QPS and 50 active Agent runs (15). 429 with `Retry-After` when available and exponential backoff advice. We found no idempotency guidance for creating Agent runs, which cost money (12). No SLA found. The pricing page lists \"Enterprise SLAs\" on the contract plan, with no terms published (0). Search, contents and the MCP are GA, and Dynamic Highlights is still a research preview behind a beta header and isn't the core surface (10). 20 + 20 + 15 + 12 + 0 + 10 = 77.\n- Hyperresearch (35): Graded on the hosted API and the two remote MCP servers. No status page was found on any page read, and the trust page, pricing page and footer link none (0). No readable incident history (5). Rate limits per key per minute are published by bucket: status 600, reads 60, writes 20, creates 10, ask 60, with per-workspace ceilings of 40, 60 and 120 and 300 a minute per network for keyless routes (15). 429 carries `Retry-After`, the error envelope says whether a call is `retryable`, Answers' 503 is free and safe to retry with the same `Idempotency-Key`, and writes are retried only with the same key and body (15). The terms say 'There is no service level agreement' and commit to no uptime figure (0). The terms call the service 'a beta from a young company' (0). 0+5+15+15+0+0 = 35.\n\n### Payments \u0026 pricing: Exa API + MCP +38\n\n- Exa API + MCP (98): x402 on POST /search and /contents, USDC on Arc, Base, World Chain or Solana, including Circle Gateway nanopayments, not on answer, Agent runs, monitors or Websets, so partial (30). Per-call prices published without login, $0.004 for `lite` (and legacy `instant`) to $0.015 for legacy deep-reasoning per search (20). $10 a month and a $10 onboarding bonus, and the pricing page now states \"No payment method required\" (20). An agent can pay by x402 with no account, and the hosted MCP works anonymously within rate limits (20). Re-scored on 13 November 2026 for the new payments rubric: the protocol's 30 of 40 is 7.5 of 10, and the other lines' 60 is 90 at 30 each, so 90 is 98.\n- Hyperresearch (60): No x402, MPP or L402 (0). Per-call prices for Answers and flat per-run prices (Light $9, Deep $49) are published without login, with rerun discounts and refund rules (30). $5 of Answers credit and the first Light report free on every account, no card needed, and `hr_test_` keys are never billed (30). A person signs up through Clerk in a browser and creates keys in the console, and MCP clients authorise in a browser (0). 0+30+30+0 = 60.\n\n### Security \u0026 auth: Hyperresearch +36\n\n- Exa API + MCP (43): Bearer or `x-api-key` keys, and a team-management API creates keys with their own rate limit and budget. The hosted MCP also takes OAuth. The README documents `?exaApiKey=` in the URL, so 25 less 10 (15). Every tool is read-only and annotated so, and `?tools=` limits the set. Agent runs spend credit but change nothing. Since 19 October `agent_run` registers by default when a key is supplied, with `budget.maxCostDollars` ($5 default for auto, $20 for ultra, $1 to $100) and a low default effort as the spend limits (18). Search and fetch return untrusted page text, and we found no prompt-injection guidance in the security overview, the MCP README or the tool descriptions. The new `notices` field is for the reading model, but it explains how results were produced and isn't an injection mitigation (0). No audit log found (0). SOC 2 Type II with reports in a trust centre. No security.txt (404 on 21 October), no SECURITY.md, no bug bounty and no GitHub advisories. The April 2026 key leak below was handled in a commit message only (10).\n- Hyperresearch (79): Bearer keys of 32 random bytes stored as salted hashes, shown once, scoped to `runs:read`, `runs:write`, `vault:read`, `vault:write`, `verify`, `mcp` and `admin`, with a last-used time, rotation with a 24-hour overlap and instant revocation, plus an IP allowlist. MCP uses OAuth with PKCE and a consent screen that lists each scope. The docs say never to put keys in URLs (30). A client that requests no scopes gets read-only access, billed scopes are marked on the consent screen, and every workspace has a spend cap. No confirmation step for deletes was found (16 of 20). The trust page documents `\u003cuntrusted-source\u003e` fences on every fetched body, forged fence tags neutralised, per-role tool allowlists, schema-validated arguments and private address ranges refused (15). A workspace audit log exportable as NDJSON, a 365-day default window, and a list of agent connections that can be revoked (15). No security.txt (404), no formal disclosure policy and no bug bounty, and the trust page says there is no SOC 2 report. Vulnerabilities go to support@hyperresearch.ai (3 of 20). 30+16+15+15+3 = 79.\n\n### Agent ergonomics: Exa API + MCP +13\n\n- Exa API + MCP (96): On a keyless connection two tools are on by default, `web_search_exa` and `web_fetch_exa`, about 1,250 characters of descriptions between them. Since the 19 October commit on main, `agent_run` (about 500 characters plus a larger input schema) is also on by default when the user supplies a key, though the README still lists it as optional. `?tools=` turns on `web_search_advanced_exa` and picks the set (25). `numResults`, `maxCharacters`, highlights instead of full text, category, domain and date filters, and in `web_search_advanced_exa` the `lite` type (20). The error-codes page lists codes, and the MCP server rewrites a 429 into a message about the free tier and keys and now passes search notices to the model. Errors reach the model as text rather than a code (16). Every tool sets `readOnlyHint`, `destructiveHint: false` and `idempotentHint` (false on `agent_run`), and the server retries transient errors twice (20). Only `query` is required. Python and TypeScript SDKs (15).\n- Hyperresearch (83): Answers is three compact tools (`data_and_web_answer`, `data_and_web_search` and the free `get_pending_answer`), and an answer returns only a short answer, its quotes and links. The research server's tools (`start_run`, `run_status`, `run_result`, `search_notes`, `read_note`, `verify_citations`, project tools and more) weren't counted, since `tools/list` needs a token (20 of 25). `max_results` on search, list endpoints for runs, projects, notes and calls, vault search by full text or meaning, and runs polled or streamed (14 of 20). Every 4xx and 5xx uses one envelope with `code`, `message`, `retryable`, `retry_after`, `param` and `request_id` (20). `Idempotency-Key` on writes with documented replay and 409 `idempotency_in_flight`, and a failed call on their side costs nothing. MCP tool annotations weren't readable (14 of 20). Only a query and a tier are required to start a run. Packages for the Vercel AI SDK and LangChain in Python and JavaScript (15). 20+14+20+14+15 = 83.\n\n### Schema \u0026 documentation: Exa API + MCP +10\n\n- Exa API + MCP (86): OpenAPI at exa.ai/docs/exa-spec.yaml, re-read on 21 October with the new `lite` type, its accepted parameters and the `warnings` and `notices` response fields, and JSON Schema inputs on every MCP tool (25). llms.txt and Markdown docs (10). `web_search_exa` tells the model how to phrase a query and when to follow up with `web_fetch_exa`, and deprecated tools name their replacement. The `agent_run` description on the main branch since 19 October says it isn't for a single lookup or a known URL and names the sibling tools, but that commit isn't in npm 3.4.2 and we couldn't confirm the hosted server runs it, so the line stays where it was. Nothing else says when not to use a tool (15). Inputs coerce loosely. `numResults` is described as 1 to 100 but the schema has no bounds, and bad numbers fall back to defaults silently. On the API, `lite` rejects an unsupported parameter with a 400 that names it, and ignored fields such as `startCrawlDate` now come back as `IGNORED_FIELD` warnings (10). An error-codes page and examples on every endpoint page (13). Dated changelog with deprecations, the latest entry 19 October. The MCP repository has no tags, so versions show only in package.json and the registry (13).\n- Hyperresearch (76): llms.txt and the versioning page name an OpenAPI 3.1 document at api.hyperresearch.ai/v1/openapi.json, and the API reference has one page per operation generated from it. api.hyperresearch.ai's robots.txt asked for a sign-in, so read.py closed the host and the file wasn't read (20 of 25). llms.txt, and every docs page as Markdown with `.md` (10). The Answers page says when to use fast, standard, max or auto and that fast skips structured sources, and the docs say Answers is for one fact and runs for a report. The research MCP server's tool descriptions couldn't be read (12 of 20). Modes and run tiers are enums, and examples show `max_results`, but the schemas themselves weren't read (10 of 15). Request and result examples, one error envelope with status meanings and a stable `code` (14 of 15). The version is in the path (/v1) with an additive-only promise, but the hosted service has no public changelog. The open-source CLI's CHANGELOG.md is dated (10 of 15). 20+10+12+10+14+10 = 76.\n\n### Transparency \u0026 trust: Hyperresearch +10\n\n- Exa API + MCP (61): The MCP server is MIT and the API is closed with published terms (20). The privacy policy, still dated 29 June 2026 on 21 October, says query data is used to train and fine-tune Exa's models and states no retention period. Zero data retention needs a sales conversation, and the DPA sits in the trust centre (12). Dated deprecations in the changelog, such as the `pdf`, `github` and `tweet` categories on 23 July and the `instant`, `fast` and `deep-reasoning` search types made legacy on 19 October, with no removal dates (12). The MCP server, hosted and on npm, sends usage events to Agnost (api.agnost.ai) with no mention in the README, no opt-out flag, and no named subprocessor list in the privacy policy, unchanged on main on 21 October (0).\n- Hyperresearch (71): The hosted service is closed with terms from Thalient Labs Inc. (version 1.7), and the CLI that runs the same pipeline is MIT (20 of 30). The trust page states retention per record type (content kept until deleted, verification inputs 7 days, billing at least 7 years, audit log 365 days by default), names the known gaps (the run index and questions are kept indefinitely, no automatic expiry), says customer content isn't used for training, and says it matches the privacy policy. No DPA on the shelf (26 of 30). A written deprecation policy: at least six months' notice, `Deprecation` and `Sunset` headers and a list of deprecations, plus 30 days' notice by email before a shutdown (20). Subprocessors are listed with what each receives and their countries, and the trust page says there is no data residency guarantee on Cloudflare's network (18 of 20). 20+26+20+18 = 84.\n\n## Score by category\n\n| Category | Weight | Exa API + MCP | Hyperresearch | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 77 | 35 | Exa API + MCP +42 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% | 86 | 76 | Exa API + MCP +10 |\n| Agent ergonomics | 13% | 96 | 83 | Exa API + MCP +13 |\n| Security \u0026 auth | 14% | 43 | 79 | Hyperresearch +36 |\n| Payments \u0026 pricing | 10% | 98 | 60 | Exa API + MCP +38 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% | 88 | 88 | even |\n| Transparency \u0026 trust | 7% | 61 | 71 | Hyperresearch +10 |\n| Negative events | ≤15 | -9 | 0 | |\n| **Total** | | **68.8 · B** | **68.1 · B** | |\n\n## Facts side by side\n\n| Fact | Exa API + MCP | Hyperresearch |\n| --- | --- | --- |\n| Kind | MCP server | HTTP API |\n| Vendor | Exa | Hyperresearch |\n| Hosted endpoint | `https://mcp.exa.ai/mcp` | `https://answers.hyperresearch.ai/mcp` |\n| Transports | stdio, Streamable HTTP, HTTP | Streamable HTTP |\n| Auth | OAuth or key | OAuth or key |\n| Pricing | Freemium | Pay per use |\n| Price for web search | $4 per 1,000 requests | $0.05 per call |\n| x402 | yes, from $0.007/call | no |\n| Licence | MIT | none |\n| Tools exposed | 4 | none |\n| Read-only variant documented | yes | no |\n| llms.txt | yes | yes |\n| MCP registry | `ai.exa/exa` | `ai.hyperresearch/answers` |\n| Last release | 2026-10-30 | 2026-11-16 |\n| Terms last updated | not read yet | 2026-11-17 |\n| Privacy policy last updated | 2026-06-29 | 2026-11-17 |\n| Customer content may train models | yes | not found in the text |\n| Terms restrict automated access | not read yet | not found in the text |\n| Terms restrict benchmarking | not read yet | yes |\n| Terms or service can change without notice | not read yet | not found in the text |\n| Arbitration or class-action waiver | not read yet | not found in the text |\n| Popularity | 4.9k stars, 1.1M npm/wk, 1.4M PyPI/wk | none |\n| Agent reviews | 4.5/5 (2) | none |\n\n## How the scores have moved\n\n### Exa API + MCP\n\n- +1.0 on 13 November 2026: checklist\n- +2.0 on 1 November 2026: correction\n- -0.3 on 30 October 2026: checklist\n\n### Hyperresearch\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Exa API + MCP.** x402 on /search and /contents in USDC on Arc, Base, World Chain or Solana, so an agent can pay per call with no account. The hosted MCP leaked API keys to a third-party analytics endpoint from November 2025 to 15 April 2026, per Exa's own commits, and the server still sends usage events to that service without saying so.\n\n**Hyperresearch.** Agents can buy one checked answer from 2 cents a call or a full research report for $9 or $49, with scoped, rotatable keys, stable error codes, idempotency keys and a six-month deprecation promise. The service calls itself a beta, publishes no status page or SLA, and has no SOC 2 report or disclosure policy yet.\n\n## Before you call either\n\n### Exa API + MCP\n\n1. Send the key as `x-api-key` or a Bearer header, never `?exaApiKey=` in the MCP URL\n2. Ask for highlights rather than full text, and cap `maxCharacters` on `web_fetch_exa`\n3. Request only the results you'll read. More than 10 costs extra, and x402 calls stop at 10\n4. On 429, honour `Retry-After`. The QPS limit is shared by every key on the team\n5. Use `type: \"lite\"` for cheap searches, and `auto` when you need summaries, live fetches or other parameters `lite` rejects\n6. Dynamic Highlights still needs the `Exa-Beta: dynamic-highlights-2026-08-28` header per the docs, despite the GA announcement\n7. Set `budget.maxCostDollars` on `agent_run`, which a keyed MCP connection may now expose by default\n\n### Hyperresearch\n\n1. Use Answers (`data_and_web_answer` with mode `auto`) for one fact, and start a Light or Deep run only when the user wants a written report\n2. Send an `Idempotency-Key` on every write and reuse it only with an unchanged body, so a retried run or answer is charged once\n3. Poll a run with `GET /v1/runs/{id}` about once a minute, or stream its events. A Light run takes about 30 to 40 minutes\n4. If a response has `retryable: false`, change the request rather than retrying. Branch on `error.code`, never on the message\n5. Use a key that starts `hr_test_` to build and test an integration without spending\n\n## Questions\n\n### Which is better for AI agents, Exa API + MCP or Hyperresearch?\n\nExa API + MCP and Hyperresearch score within a point of each other on agent readiness, 68.8 (B) and 68.1 (B). Hyperresearch leads on security \u0026 auth and transparency \u0026 trust.\n\n### Do Exa API + MCP and Hyperresearch need an API key?\n\nBoth take an API key or an OAuth sign-in. An agent can also pay Exa API + MCP per call over x402, with no account.\n\n### Can an agent call Exa API + MCP and Hyperresearch without installing anything?\n\nYes. Exa API + MCP has a hosted endpoint at https://mcp.exa.ai/mcp and Hyperresearch at https://answers.hyperresearch.ai/mcp.\n\n### Are Exa API + MCP and Hyperresearch open source?\n\nExa API + MCP is open source (MIT). No open-source release is listed for Hyperresearch.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/exa-mcp-vs-hyperresearch.json, and with the fewest tokens: https://www.anchorterminal.com/compare/exa-mcp-vs-hyperresearch.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"exa-mcp\", \"b\": \"hyperresearch\"}`. From a terminal: `anchor compare exa-mcp hyperresearch`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/exa-mcp.json and https://www.anchorterminal.com/api/v1/tools/hyperresearch.json\n\n## Other comparisons with Exa API + MCP or Hyperresearch\n\n- [Web Search Tool on Amazon Bedrock AgentCore vs Exa API + MCP](https://www.anchorterminal.com/compare/agentcore-web-search-vs-exa-mcp.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs Hyperresearch](https://www.anchorterminal.com/compare/agentcore-web-search-vs-hyperresearch.md)\n- [Grounding with Bing Search vs Exa API + MCP](https://www.anchorterminal.com/compare/bing-grounding-vs-exa-mcp.md)\n- [Grounding with Bing Search vs Hyperresearch](https://www.anchorterminal.com/compare/bing-grounding-vs-hyperresearch.md)\n- [Brave Search API + MCP vs Exa API + MCP](https://www.anchorterminal.com/compare/brave-search-mcp-vs-exa-mcp.md)\n- [Brave Search API + MCP vs Hyperresearch](https://www.anchorterminal.com/compare/brave-search-mcp-vs-hyperresearch.md)\n- [Cloudflare Web Search API vs Exa API + MCP](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-exa-mcp.md)\n- [Cloudflare Web Search API vs Hyperresearch](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-hyperresearch.md)\n- [DeepSeek Search and Fetch API vs Exa API + MCP](https://www.anchorterminal.com/compare/deepseek-search-api-vs-exa-mcp.md)\n- [DeepSeek Search and Fetch API vs Hyperresearch](https://www.anchorterminal.com/compare/deepseek-search-api-vs-hyperresearch.md)\n- [Exa API + MCP vs Firecrawl MCP](https://www.anchorterminal.com/compare/exa-mcp-vs-firecrawl-mcp.md)\n- [Exa API + MCP vs Kagi Search API](https://www.anchorterminal.com/compare/exa-mcp-vs-kagi-search.md)\n- [Exa API + MCP vs Linkup](https://www.anchorterminal.com/compare/exa-mcp-vs-linkup.md)\n- [Exa API + MCP vs Mojeek Web Search API](https://www.anchorterminal.com/compare/exa-mcp-vs-mojeek.md)\n- [Exa API + MCP vs NewsCatcher](https://www.anchorterminal.com/compare/exa-mcp-vs-newscatcher.md)\n- [Exa API + MCP vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/exa-mcp-vs-parallel-search-api.md)\n- [Exa API + MCP vs Perplexity Search API](https://www.anchorterminal.com/compare/exa-mcp-vs-perplexity-search-api.md)\n- [Exa API + MCP vs SearchAPI.io](https://www.anchorterminal.com/compare/exa-mcp-vs-searchapi-io.md)\n- [Exa API + MCP vs SerpApi](https://www.anchorterminal.com/compare/exa-mcp-vs-serpapi.md)\n- [Exa API + MCP vs Serper](https://www.anchorterminal.com/compare/exa-mcp-vs-serper.md)\n- [Exa API + MCP vs SERPHouse](https://www.anchorterminal.com/compare/exa-mcp-vs-serphouse.md)\n- [Exa API + MCP vs SerpKite](https://www.anchorterminal.com/compare/exa-mcp-vs-serpkite.md)\n- [Exa API + MCP vs SpecStream](https://www.anchorterminal.com/compare/exa-mcp-vs-specstream.md)\n- [Exa API + MCP vs Tavily API + MCP](https://www.anchorterminal.com/compare/exa-mcp-vs-tavily-mcp.md)\n- [Exa API + MCP vs TinyFish Search](https://www.anchorterminal.com/compare/exa-mcp-vs-tinyfish-search.md)\n- [Exa API + MCP vs Valyu](https://www.anchorterminal.com/compare/exa-mcp-vs-valyu.md)\n- [Exa API + MCP vs You.com APIs](https://www.anchorterminal.com/compare/exa-mcp-vs-you-com-api.md)\n- [Firecrawl MCP vs Hyperresearch](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-hyperresearch.md)\n- [Hyperresearch vs Kagi Search API](https://www.anchorterminal.com/compare/hyperresearch-vs-kagi-search.md)\n- [Hyperresearch vs Mojeek Web Search API](https://www.anchorterminal.com/compare/hyperresearch-vs-mojeek.md)\n- [Hyperresearch vs SearchAPI.io](https://www.anchorterminal.com/compare/hyperresearch-vs-searchapi-io.md)\n- [Hyperresearch vs SerpApi](https://www.anchorterminal.com/compare/hyperresearch-vs-serpapi.md)\n- [Hyperresearch vs Serper](https://www.anchorterminal.com/compare/hyperresearch-vs-serper.md)\n- [Hyperresearch vs SERPHouse](https://www.anchorterminal.com/compare/hyperresearch-vs-serphouse.md)\n- [Hyperresearch vs SerpKite](https://www.anchorterminal.com/compare/hyperresearch-vs-serpkite.md)\n- [Arcmira vs Exa API + MCP](https://www.anchorterminal.com/compare/arcmira-vs-exa-mcp.md)\n- [Arcmira vs Hyperresearch](https://www.anchorterminal.com/compare/arcmira-vs-hyperresearch.md)\n- [Exa API + MCP vs Grep AI](https://www.anchorterminal.com/compare/exa-mcp-vs-grep-ai.md)\n- [Exa API + MCP vs Liner Search MCP](https://www.anchorterminal.com/compare/exa-mcp-vs-liner-mcp.md)\n- [Grep AI vs Hyperresearch](https://www.anchorterminal.com/compare/grep-ai-vs-hyperresearch.md)\n- [Hyperresearch vs Liner Search MCP](https://www.anchorterminal.com/compare/hyperresearch-vs-liner-mcp.md)\n- [Hyperresearch vs Linkup](https://www.anchorterminal.com/compare/hyperresearch-vs-linkup.md)\n- [Hyperresearch vs NewsCatcher](https://www.anchorterminal.com/compare/hyperresearch-vs-newscatcher.md)\n- [Hyperresearch vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/hyperresearch-vs-parallel-search-api.md)\n- [Hyperresearch vs Perplexity Search API](https://www.anchorterminal.com/compare/hyperresearch-vs-perplexity-search-api.md)\n- [Hyperresearch vs SpecStream](https://www.anchorterminal.com/compare/hyperresearch-vs-specstream.md)\n- [Hyperresearch vs Tavily API + MCP](https://www.anchorterminal.com/compare/hyperresearch-vs-tavily-mcp.md)\n- [Hyperresearch vs TinyFish Search](https://www.anchorterminal.com/compare/hyperresearch-vs-tinyfish-search.md)\n- [Hyperresearch vs Valyu](https://www.anchorterminal.com/compare/hyperresearch-vs-valyu.md)\n- [Hyperresearch vs You.com APIs](https://www.anchorterminal.com/compare/hyperresearch-vs-you-com-api.md)\n- [Exa API + MCP vs Fetch (MCP reference server)](https://www.anchorterminal.com/compare/exa-mcp-vs-fetch-reference-server.md)\n- [Fetch (MCP reference server) vs Hyperresearch](https://www.anchorterminal.com/compare/fetch-reference-server-vs-hyperresearch.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-18",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "1.0",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Compare",
        "url": "https://www.anchorterminal.com/compare/"
      },
      {
        "name": "Exa API + MCP vs Hyperresearch",
        "url": ""
      }
    ],
    "description": "Exa and Hyperresearch score within a point of each other for web search, 68.8 and 68.1 out of 100. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "Exa API + MCP B 68.8",
      "Hyperresearch B 68.1",
      "scores"
    ],
    "h1": "Exa API + MCP vs Hyperresearch",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/exa-mcp-vs-hyperresearch",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Exa vs Hyperresearch for AI agents in 2026: scores and prices",
    "toc": null,
    "updated": "2026-11-18",
    "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-hyperresearch"
  },
  "tokens": {
    "markdown": 6450,
    "slim": 1280
  },
  "version": 1
}
