{
  "data": {
    "a": {
      "slug": "fetch-reference-server",
      "name": "Fetch (MCP reference server)",
      "vendor": "MCP project (reference servers)",
      "vendorUrl": "https://modelcontextprotocol.io",
      "company": "modelcontextprotocol.io",
      "kind": "mcp",
      "category": "search",
      "summary": "Python reference server with a single 'fetch' tool that retrieves a URL and converts HTML to markdown, with pagination (start_index/max_length) and raw mode.",
      "url": "https://www.anchorterminal.com/tools/fetch-reference-server",
      "markdownUrl": "https://www.anchorterminal.com/tools/fetch-reference-server.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/fetch-reference-server.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/fetch-reference-server.json",
      "dns": "fetch-reference-server.grade.anchorterminal.com",
      "repo": "https://github.com/modelcontextprotocol/servers",
      "license": "MIT and Apache-2.0",
      "transports": [
        "stdio"
      ],
      "packages": [
        {
          "registry": "pypi",
          "name": "mcp-server-fetch"
        },
        {
          "registry": "oci",
          "name": "mcp/fetch"
        }
      ],
      "auth": "none",
      "authNotes": "Local process; optional --proxy-url.",
      "pricing": "free",
      "pricingNotes": "Open source.",
      "priceSummary": "Free · OSS",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "Local reference server, no payments.",
        "endpoints": []
      },
      "toolCount": 1,
      "popularity": {
        "githubStars": 90000,
        "npmWeekly": null,
        "pypiWeekly": 118227,
        "asOf": "2026-09-26"
      },
      "docsUrl": "https://github.com/modelcontextprotocol/servers/blob/main/src/fetch/README.md",
      "capabilities": [
        "web.fetch"
      ],
      "tags": [
        "reference",
        "local",
        "open-source",
        "python"
      ],
      "lastRelease": "2026-10-28",
      "graded": true,
      "disclosure": "MCP started at Anthropic, which makes the Claude models our research agents and review panel run on (Anthropic donated it to the Agentic AI Foundation, a directed fund under the Linux Foundation, in December 2025), and this server is graded by the same checklist as every other listing.",
      "anchor": {
        "graded": true,
        "score": 63.8,
        "grade": "B",
        "agentReady": false,
        "rank": 615,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 20,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 93,
          "maintenance": 72,
          "payments": 90,
          "reliability": 55,
          "schema": 70,
          "security": 47,
          "transparency": 75
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-04"
        },
        "negative": -6,
        "negativeNotes": [
          "-3, released fixes of the server's own described flaws with no advisory. 2026.10.10 (tag v1.0.0, 10 October 2026) stopped a model-supplied URL or any redirect hop from reaching loopback, RFC 1918, link-local and cloud metadata addresses (315ad505, #4838), and 2026.10.28 (tag v2.2.0) closed IPv4-compatible IPv6 addresses such as `::127.0.0.1` slipping past that guard (0b958325, closing public issue #5181). SECURITY.md counts such flaws as vulnerabilities, and neither commit cites a GHSA id. One folded term. https://github.com/modelcontextprotocol/servers/blob/main/src/fetch/README.md",
          "-3, published behaviour changed for existing clients with word only on release day. 2026.10.10 refuses private, loopback and link-local addresses that earlier versions fetched unless the server is started with `--allow-private-ips`, and 2026.10.28 refuses an autonomous fetch when robots.txt answers 5xx. There is no changelog for this package and no pre-release tag; the README changed with each release. One folded term. https://github.com/modelcontextprotocol/servers/blob/main/src/fetch/README.md"
        ],
        "verdict": "One read-only tool of about 300 tokens, with `max_length` and `start_index` paging and a hint giving the next offset. Since 2026.10.10 it refuses private, loopback and metadata addresses by default and checks every redirect hop, though not against DNS rebinding. Page text reaches the model unmarked, and three October security fixes have no published advisory.",
        "bestFor": "Reading a known URL as Markdown in a local or sandboxed agent, at no cost.",
        "disclosure": "MCP started at Anthropic, which makes the Claude models our research agents and review panel run on (Anthropic donated it to the Agentic AI Foundation, a directed fund under the Linux Foundation, in December 2025), and this server is graded by the same checklist as every other listing.",
        "strengths": [
          "One tool of about 300 tokens, with `max_length` and `start_index` paging and a hint giving the next offset",
          "Refuses private, loopback and cloud metadata addresses by default since 2026.10.10, checking every redirect hop",
          "Annotated read-only, non-destructive and idempotent since 2026.10.19",
          "Four releases in October 2026, each running ruff, pyright and pytest before publishing",
          "No telemetry and no credentials, MIT licence"
        ],
        "weaknesses": [
          "The address guard doesn't cover DNS rebinding or hosts only a proxy can resolve, per its README",
          "Page text reaches the model unmarked, with no prompt-injection guidance",
          "Three fixes merged on 24 October name GHSA ids that aren't published, and two other security fixes cite none",
          "CalVer versions with no changelog for this package, classed 4 - Beta",
          "No entry in the official MCP registry"
        ],
        "agentNotes": [
          "Fetch with the 5,000-character default and continue from the `start_index` the truncation note gives",
          "Expect a refusal for private, loopback and metadata addresses unless the operator started the server with `--allow-private-ips`",
          "Expect empty bodies from JavaScript-rendered sites and switch to a browser tool",
          "Treat a robots.txt refusal (a disallow, or a 401, 403 or 5xx answer) as final for autonomous calls and tell the user",
          "Use `raw: true` only for non-HTML content. It skips the Markdown conversion and returns the page as served"
        ],
        "metrics": {
          "kind": "local",
          "measured": false
        },
        "reviewCount": 2,
        "avgRating": 4,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "B",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 63.8
          }
        ],
        "editorialScores": {
          "ergonomics": 93,
          "maintenance": 72,
          "payments": 90,
          "reliability": 55,
          "schema": 70,
          "security": 47,
          "transparency": 76
        },
        "provenanceScore": 74,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-04",
            "maintenance": "2026-11-04",
            "payments": "2026-11-04",
            "reliability": "2026-11-04",
            "schema": "2026-11-04",
            "security": "2026-11-04",
            "transparency": "2026-11-04"
          },
          "last": "2026-11-04",
          "lastMoved": "2026-11-13",
          "oldest": "2026-11-04",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "claudeCode": "claude mcp add fetch -- uvx mcp-server-fetch",
        "config": {
          "mcpServers": {
            "fetch": {
              "args": [
                "mcp-server-fetch"
              ],
              "command": "uvx"
            }
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/web.fetch",
        "tool": "https://letme.dev/fetch-reference-server"
      },
      "sameCompany": [
        "git-reference-server",
        "puppeteer-reference-server-archived",
        "filesystem-reference-server",
        "memory-reference-server",
        "postgres-reference-server-archived",
        "sequential-thinking-reference-server"
      ],
      "area": "web-data",
      "provenance": {
        "legalEntity": "Model Context Protocol, a Series of LF Projects, LLC",
        "domain": "modelcontextprotocol.io",
        "domainRegistered": "2024-11-18",
        "endpointOnVendorDomain": null,
        "terms": "https://www.lfprojects.org/policies/terms-of-use/",
        "privacy": "https://www.lfprojects.org/policies/privacy-policy/",
        "statusPage": "",
        "changelog": "https://github.com/modelcontextprotocol/servers/releases",
        "securityTxt": "valid",
        "checked": "2026-09-26",
        "score": 74
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/fetch-reference-server.json",
      "live": {
        "slug": "fetch-reference-server",
        "versions": [
          {
            "registry": "github",
            "name": "modelcontextprotocol/servers",
            "version": "v2.5.0",
            "released": "2026-11-18",
            "seenAt": "2026-11-18T17:47:28.811363734Z"
          },
          {
            "registry": "pypi",
            "name": "mcp-server-fetch",
            "version": "2026.11.18",
            "released": "2026-11-18",
            "seenAt": "2026-11-18T17:47:26.896387057Z"
          }
        ],
        "githubStars": 92087,
        "pypiWeekly": 224716,
        "securityTxt": {
          "url": "https://modelcontextprotocol.io/.well-known/security.txt",
          "state": "valid",
          "checkedAt": "2026-11-18T16:30:41.966998389Z"
        },
        "domain": {
          "domain": "modelcontextprotocol.io",
          "checkedAt": "2026-11-15T15:41:55.926260029Z"
        },
        "pages": [
          {
            "url": "https://www.lfprojects.org/policies/privacy-policy/",
            "kind": "privacy",
            "status": 200,
            "checkedAt": "2026-11-18T22:05:13.289420658Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "38cea2fa08bd"
          },
          {
            "url": "https://www.lfprojects.org/policies/terms-of-use/",
            "kind": "terms",
            "status": 200,
            "checkedAt": "2026-11-18T22:05:16.390179222Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "6b8804f51317"
          }
        ],
        "github": {
          "repo": "modelcontextprotocol/servers",
          "checkedAt": "2026-11-16T12:30:28.60498744Z",
          "stars": 92038,
          "archived": false,
          "issuesEnabled": true,
          "pushedAt": "2026-11-12T05:37:52Z",
          "openIssues": 20,
          "openPRs": 2,
          "issuesOpened90d": 347,
          "issuesClosed90d": 565,
          "prsMerged90d": 324,
          "ci": {
            "branch": "main",
            "runs": 50,
            "success": 44,
            "failure": 0,
            "other": 6,
            "latest": "success",
            "latestAt": "2026-11-11T06:51:16Z"
          },
          "advisories": [
            {
              "ghsa": "GHSA-p9cv-8g75-4xcg",
              "severity": "medium",
              "published": "2026-11-11T07:28:07Z"
            },
            {
              "ghsa": "GHSA-q74p-4wrc-q7w6",
              "severity": "medium",
              "published": "2026-11-11T07:27:42Z"
            },
            {
              "ghsa": "GHSA-f9hh-cmx9-2f23",
              "severity": "low",
              "published": "2026-11-11T07:27:04Z"
            },
            {
              "ghsa": "GHSA-6hqx-gqrx-c5r2",
              "severity": "high",
              "published": "2026-11-11T07:25:22Z"
            },
            {
              "ghsa": "GHSA-3rxj-6jhw-qfv7",
              "severity": "low",
              "published": "2026-11-11T07:25:00Z"
            },
            {
              "ghsa": "GHSA-7m4x-rv66-mxhh",
              "severity": "medium",
              "published": "2026-11-11T07:24:37Z"
            },
            {
              "ghsa": "GHSA-w766-5x43-whvw",
              "severity": "medium",
              "published": "2026-10-28T21:13:40Z"
            },
            {
              "ghsa": "GHSA-mvf5-2qqv-rg3c",
              "severity": "medium",
              "published": "2026-10-25T00:19:52Z"
            },
            {
              "ghsa": "GHSA-hhwq-wxfx-cj7g",
              "severity": "low",
              "published": "2026-10-25T00:19:37Z"
            },
            {
              "ghsa": "GHSA-53mr-w429-c597",
              "severity": "low",
              "published": "2026-10-25T00:19:21Z"
            },
            {
              "ghsa": "GHSA-v38p-wf49-hx2j",
              "severity": "medium",
              "published": "2026-10-25T00:19:06Z"
            },
            {
              "ghsa": "GHSA-66qx-2266-pmj6",
              "severity": "low",
              "published": "2026-10-25T00:18:52Z"
            },
            {
              "ghsa": "GHSA-7rgq-gccq-qphx",
              "severity": "medium",
              "published": "2026-10-25T00:18:38Z"
            },
            {
              "ghsa": "GHSA-4gxg-m5jx-9j57",
              "severity": "medium",
              "published": "2026-10-25T00:18:21Z"
            },
            {
              "ghsa": "GHSA-3jqg-r5pp-rmp2",
              "severity": "low",
              "published": "2026-10-25T00:15:37Z"
            },
            {
              "ghsa": "GHSA-vjqx-cfc4-9h6v",
              "cve": "CVE-2026-27735",
              "severity": "medium",
              "published": "2026-02-25T23:21:57Z"
            },
            {
              "ghsa": "GHSA-j22h-9j4x-23w5",
              "cve": "CVE-2025-68145",
              "severity": "medium",
              "published": "2025-12-17T16:04:43Z"
            },
            {
              "ghsa": "GHSA-9xwc-hfwc-8w59",
              "cve": "CVE-2025-68144",
              "severity": "medium",
              "published": "2025-12-17T16:01:56Z"
            },
            {
              "ghsa": "GHSA-5cgr-j3jf-jw3v",
              "cve": "CVE-2025-68143",
              "severity": "medium",
              "published": "2025-12-17T15:55:26Z"
            },
            {
              "ghsa": "GHSA-hc55-p739-j48w",
              "cve": "CVE-2025-53110",
              "severity": "high",
              "published": "2025-07-01T18:39:04Z"
            },
            {
              "ghsa": "GHSA-q66q-fx2p-7w4m",
              "cve": "CVE-2025-53109",
              "severity": "high",
              "published": "2025-07-01T18:38:24Z"
            }
          ],
          "replies": {
            "sampled": 25,
            "unanswered": 12,
            "medianDays": 0
          }
        },
        "updatedAt": "2026-11-18T22:05:16.390179222Z"
      }
    },
    "answer": "Hyperresearch scores 68.1 (B) on agent readiness against Fetch (MCP reference server)'s 63.8 (B), and leads in 3 of 7 scored categories. Fetch (MCP reference server) leads on reliability, agent ergonomics and payments \u0026 pricing.",
    "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": 32,
        "category": "security",
        "leads": "hyperresearch",
        "name": "Security \u0026 auth",
        "reasons": {
          "a": "No credentials to leak and nothing to scope, so the middle band (20). GET only. Since 2026.10.10 the server refuses private, loopback, link-local and cloud metadata addresses by default and checks the robots.txt request and every redirect hop the same way, with `--allow-private-ips` to turn the guard off. The README says it doesn't cover DNS rebinding between the check and the connection, or a host only a proxy can resolve (15, judgement call). It returns untrusted page text unmarked, and the README has no prompt-injection guidance (0). No call log (0). SECURITY.md, rewritten on 29 September 2026 and on main since the v1.0.0 tag, names fetch in scope, takes private reports through GitHub and publishes advisories once a fixed release is out. No bounty or certification. Graded as the filesystem and sequential-thinking servers (12). OSV holds no advisory for mcp-server-fetch. Three fixes merged on 24 October from branches named for GHSA-66qx-2266-pmj6, GHSA-3jqg-r5pp-rmp2 and GHSA-v38p-wf49-hx2j shipped in 2026.10.24. None is in OSV or in GitHub's own advisory database on 4 November, so none is published as far as can be read and none is counted (as the filesystem server's four). 20+15+0+0+12 = 47.",
          "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": 47,
          "b": 79
        }
      },
      {
        "by": 30,
        "category": "payments",
        "leads": "fetch-reference-server",
        "name": "Payments \u0026 pricing",
        "reasons": {
          "a": "Free, self-hosted, nothing to buy, so 20 + 20 + 20. No payment protocol (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90.",
          "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": 90,
          "b": 60
        }
      },
      {
        "by": 20,
        "category": "reliability",
        "leads": "fetch-reference-server",
        "name": "Reliability",
        "reasons": {
          "a": "Scored as a local stdio package. Official PyPI package mcp-server-fetch and the mcp/fetch Docker image, Python 3.10 or later stated (20). The monorepo's python.yml runs ruff, pyright and pytest for fetch on push, with 13 test files for this server. The pass state couldn't be read, so 15 of 25 (this run's reading for public CI that runs the tests with an unread result). The October releases close filed issues, among them #4838 (private addresses), #767, #4988, #5134, #5158, #5181, #5197 and #5199; the open issue list couldn't be read (15). CalVer versions (2026.10.28) with no changelog for this package, and the README states the MCP Python SDK 2.x requirement (5). The classifier still says 4 - Beta and the repository calls its servers reference implementations, not production-ready (0). 20+15+15+5+0 = 55.",
          "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": 55,
          "b": 35
        }
      },
      {
        "by": 16,
        "category": "maintenance",
        "leads": "hyperresearch",
        "name": "Maintenance \u0026 community",
        "reasons": {
          "a": "2026.10.28, stamped and tagged v2.2.0 on 28 October 2026, 7 days before this check (30). Releases of this package in the 90 days from 6 August are 2026.8.18 (an SDK pin and a README note), 2026.10.10 (tag v1.0.0), 2026.10.19 (tag v2.0.0), 2026.10.24 (tag v2.1.0) and 2026.10.28, the last four with code changes. Dates come from the repository's tags and CalVer stamps, since pypi.org didn't resolve from our shell today. The package has no separate CLI or plugin (20). Fixes for fetch merged through October cite issues filed for them; reply times on issues couldn't be read (12). Not in the official MCP registry on 4 November (a search for server-fetch returns nothing), though the README carries an `mcp-name` for io.github.modelcontextprotocol/server-fetch (0). Current SDK (`mcp\u003e=2.3,\u003c3`), CI on push, a dependency sweep and a pip-audit step before each release (10). 30+20+12+0+10 = 72.",
          "b": "The pricing and about pages were updated on 17 November 2026, and the open-source CLI that the hosted service runs was tagged v0.13.3 on 16 November (30). Four tagged CLI releases in the 90 days to this check: v0.13.0 (27 October), v0.13.1 (9 November), v0.13.2 (12 November), v0.13.3 (16 November) (20). The CLI changelog credits fixes to issues and pull requests from outside contributors (#71, #201 to #206). We didn't read the issue threads (15 of 25). `ai.hyperresearch/hyperresearch` and `ai.hyperresearch/answers` are in the official MCP registry under the vendor's domain namespace (15). The repository has CI and publish workflows, and AI SDK and LangChain packages are published (8 of 10). 30+20+15+15+8 = 88."
        },
        "scores": {
          "a": 72,
          "b": 88
        }
      },
      {
        "by": 10,
        "category": "ergonomics",
        "leads": "fetch-reference-server",
        "name": "Agent ergonomics",
        "reasons": {
          "a": "One tool, about 1,160 characters of definition, roughly 300 tokens (25). `max_length` and `start_index` page through long documents, and a truncated response names the next `start_index` (20). Invalid input returns INVALID_PARAMS, and a robots.txt or private-address refusal explains why and what the user can do (16). Since 2026.10.19 the tool carries readOnlyHint true, destructiveHint false, idempotentHint true and openWorldHint true, and a GET is safe to repeat (20). Only `url` is required and the defaults are sensible. Python only, plus a Docker image (12). 25+20+16+20+12 = 93.",
          "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": 93,
          "b": 83
        }
      },
      {
        "by": 6,
        "category": "schema",
        "leads": "hyperresearch",
        "name": "Schema \u0026 documentation",
        "reasons": {
          "a": "The one tool takes a typed JSON Schema built from its type hints and Pydantic fields, validated strictly (25). No llms.txt. The README is Markdown on GitHub (5). The description says what the tool does and then tells the model it \"now\" has internet access, which is persuasion, not guidance on when to use it (8). `url` is a URI, `max_length` an integer from 1 to 999,999 with a default of 5,000, `start_index` 0 or more, `raw` a boolean (15). Configuration examples for several clients. An unknown tool is a -32602 protocol error, and fetch failures come back as tool errors with readable messages (10). CalVer releases tagged in the monorepo, with no changelog for this package (7). 25+5+8+15+10+7 = 70.",
          "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": 70,
          "b": 76
        }
      }
    ],
    "facts": [
      {
        "a": "MCP server",
        "b": "HTTP API",
        "name": "Kind"
      },
      {
        "a": "MCP project (reference servers)",
        "b": "Hyperresearch",
        "name": "Vendor"
      },
      {
        "a": "no (local only)",
        "b": "https://answers.hyperresearch.ai/mcp",
        "name": "Hosted endpoint"
      },
      {
        "a": "stdio",
        "b": "Streamable HTTP",
        "name": "Transports"
      },
      {
        "a": "None",
        "b": "OAuth or key",
        "name": "Auth"
      },
      {
        "a": "Free",
        "b": "Pay per use",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "MIT and Apache-2.0",
        "b": "none",
        "name": "Licence"
      },
      {
        "a": "1",
        "b": "none",
        "name": "Tools exposed"
      },
      {
        "a": "yes",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "no",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "not listed",
        "b": "ai.hyperresearch/answers",
        "name": "MCP registry"
      },
      {
        "a": "2026-10-28",
        "b": "2026-11-16",
        "name": "Last release"
      },
      {
        "a": "2021-09-08",
        "b": "2026-11-17",
        "name": "Terms last updated"
      },
      {
        "a": "2023-03-15",
        "b": "2026-11-17",
        "name": "Privacy policy last updated"
      },
      {
        "a": "not found in the text",
        "b": "not found in the text",
        "name": "Customer content may train models"
      },
      {
        "a": "not found in the text",
        "b": "not found in the text",
        "name": "Terms restrict automated access"
      },
      {
        "a": "not found in the text",
        "b": "yes",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "not found in the text",
        "b": "not found in the text",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "not found in the text",
        "b": "not found in the text",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "90k stars, 118k PyPI/wk",
        "b": "none",
        "name": "Popularity"
      },
      {
        "a": "4/5 (2)",
        "b": "none",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "Hyperresearch scores 68.1 (B) on agent readiness against Fetch (MCP reference server)'s 63.8 (B), and leads in 3 of 7 scored categories. Fetch (MCP reference server) leads on reliability, agent ergonomics and payments \u0026 pricing.",
        "question": "Which is better for AI agents, Fetch (MCP reference server) or Hyperresearch?"
      },
      {
        "answer": "Fetch (MCP reference server) needs no key. Hyperresearch takes an API key or an OAuth sign-in.",
        "question": "Do Fetch (MCP reference server) and Hyperresearch need an API key?"
      },
      {
        "answer": "Fetch (MCP reference server) runs on your own machine, with no hosted endpoint listed. Hyperresearch has a hosted endpoint at https://answers.hyperresearch.ai/mcp.",
        "question": "Can an agent call Fetch (MCP reference server) and Hyperresearch without installing anything?"
      },
      {
        "answer": "Fetch (MCP reference server) is open source (MIT and Apache-2.0). No open-source release is listed for Hyperresearch.",
        "question": "Are Fetch (MCP reference server) and Hyperresearch open source?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 55 against 35",
          "Agent ergonomics, 93 against 83",
          "Payments \u0026 pricing, 90 against 60"
        ],
        "also": [
          "No key needed to call it",
          "Runs on your own machine",
          "Open source"
        ],
        "goodFor": "Reading a known URL as Markdown in a local or sandboxed agent, at no cost.",
        "slug": "fetch-reference-server",
        "watchFor": "The address guard doesn't cover DNS rebinding or hosts only a proxy can resolve, per its README"
      },
      {
        "aheadOn": [
          "Schema \u0026 documentation, 76 against 70",
          "Security \u0026 auth, 79 against 47",
          "Maintenance \u0026 community, 88 against 72"
        ],
        "also": [
          "A hosted endpoint, with nothing to install",
          "Free to start without a card",
          "No incidents deducted, where Fetch (MCP reference server) loses 6 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": {
      "fetch-reference-server": [
        {
          "causes": [
            "method"
          ],
          "date": "2026-11-13",
          "delta": 3.7,
          "from": 60.1,
          "fromGrade": "C",
          "to": 63.8,
          "toGrade": "B"
        },
        {
          "causes": [
            "security",
            "product",
            "correction",
            "event"
          ],
          "date": "2026-11-04",
          "delta": 2.5,
          "from": 57.6,
          "fromGrade": "C",
          "to": 60.1,
          "toGrade": "C"
        },
        {
          "causes": [
            "evidence"
          ],
          "date": "2026-10-28",
          "delta": 0,
          "from": 57.6,
          "fromGrade": "C",
          "to": 57.6,
          "toGrade": "C"
        }
      ],
      "hyperresearch": null
    },
    "job": {
      "capability": "web.fetch",
      "name": "Fetching pages"
    },
    "others": [
      {
        "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-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-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-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-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-hyperresearch.json",
        "title": "Exa API + MCP vs Hyperresearch",
        "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-hyperresearch"
      },
      {
        "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-hyperresearch.json",
        "title": "Arcmira vs Hyperresearch",
        "url": "https://www.anchorterminal.com/compare/arcmira-vs-hyperresearch"
      },
      {
        "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/deepseek-search-api-vs-fetch-reference-server.json",
        "title": "DeepSeek Search and Fetch API vs Fetch (MCP reference server)",
        "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-fetch-reference-server"
      },
      {
        "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-kagi-search.json",
        "title": "Fetch (MCP reference server) vs Kagi Search API",
        "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-kagi-search"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-linkup.json",
        "title": "Fetch (MCP reference server) vs Linkup",
        "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-linkup"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-lordevo-shop.json",
        "title": "Fetch (MCP reference server) vs Lordevo Shop",
        "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-lordevo-shop"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-parallel-search-api.json",
        "title": "Fetch (MCP reference server) vs Parallel Search and Task APIs",
        "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-parallel-search-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-serphouse.json",
        "title": "Fetch (MCP reference server) vs SERPHouse",
        "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-serphouse"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-serpkite.json",
        "title": "Fetch (MCP reference server) vs SerpKite",
        "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-serpkite"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-tavily-mcp.json",
        "title": "Fetch (MCP reference server) vs Tavily API + MCP",
        "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-tavily-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-tinyfish-search.json",
        "title": "Fetch (MCP reference server) vs TinyFish Search",
        "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-tinyfish-search"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-valyu.json",
        "title": "Fetch (MCP reference server) vs Valyu",
        "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-valyu"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-you-com-api.json",
        "title": "Fetch (MCP reference server) vs You.com APIs",
        "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-you-com-api"
      }
    ],
    "panel": null,
    "scores": [
      {
        "by": 20,
        "edge": "fetch-reference-server",
        "fetch-reference-server": 55,
        "hyperresearch": 35,
        "key": "reliability",
        "name": "Reliability",
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 6,
        "edge": "hyperresearch",
        "fetch-reference-server": 70,
        "hyperresearch": 76,
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "weight": 13
      },
      {
        "by": 10,
        "edge": "fetch-reference-server",
        "fetch-reference-server": 93,
        "hyperresearch": 83,
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "weight": 13
      },
      {
        "by": 32,
        "edge": "hyperresearch",
        "fetch-reference-server": 47,
        "hyperresearch": 79,
        "key": "security",
        "name": "Security \u0026 auth",
        "weight": 14
      },
      {
        "by": 30,
        "edge": "fetch-reference-server",
        "fetch-reference-server": 90,
        "hyperresearch": 60,
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 16,
        "edge": "hyperresearch",
        "fetch-reference-server": 72,
        "hyperresearch": 88,
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "weight": 7
      },
      {
        "by": 4,
        "edge": "fetch-reference-server",
        "fetch-reference-server": 75,
        "hyperresearch": 71,
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "weight": 7
      }
    ],
    "summary": "Hyperresearch scores 68.1 (B) on agent readiness against Fetch (MCP reference server)'s 63.8 (B), and leads in 3 of 7 scored categories. Fetch (MCP reference server) leads on reliability, agent ergonomics and payments \u0026 pricing. Both do fetching pages.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "fetch-reference-server": "One read-only tool of about 300 tokens, with `max_length` and `start_index` paging and a hint giving the next offset. Since 2026.10.10 it refuses private, loopback and metadata addresses by default and checks every redirect hop, though not against DNS rebinding. Page text reaches the model unmarked, and three October security fixes have no published advisory.",
      "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/fetch-reference-server-vs-hyperresearch",
    "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-hyperresearch.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-hyperresearch.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-hyperresearch.min.md"
  },
  "markdown": "Hyperresearch scores 68.1 (B) on agent readiness against Fetch (MCP reference server)'s 63.8 (B), and leads in 3 of 7 scored categories. Fetch (MCP reference server) leads on reliability, agent ergonomics and payments \u0026 pricing. Both do fetching pages.\n\n- Fetch (MCP reference server): grade B, 63.8/100, rank #615 of 1557. Markdown https://www.anchorterminal.com/tools/fetch-reference-server.md · JSON https://www.anchorterminal.com/api/v1/tools/fetch-reference-server.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### Fetch (MCP reference server) (B)\n\nGood for: Reading a known URL as Markdown in a local or sandboxed agent, at no cost.\n\nAhead on:\n- Reliability, 55 against 35\n- Agent ergonomics, 93 against 83\n- Payments \u0026 pricing, 90 against 60\n\nAlso in its favour:\n- No key needed to call it\n- Runs on your own machine\n- Open source\n\nWatch for: The address guard doesn't cover DNS rebinding or hosts only a proxy can resolve, per its README\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- Schema \u0026 documentation, 76 against 70\n- Security \u0026 auth, 79 against 47\n- Maintenance \u0026 community, 88 against 72\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n- Free to start without a card\n- No incidents deducted, where Fetch (MCP reference server) loses 6 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### Security \u0026 auth: Hyperresearch +32\n\n- Fetch (MCP reference server) (47): No credentials to leak and nothing to scope, so the middle band (20). GET only. Since 2026.10.10 the server refuses private, loopback, link-local and cloud metadata addresses by default and checks the robots.txt request and every redirect hop the same way, with `--allow-private-ips` to turn the guard off. The README says it doesn't cover DNS rebinding between the check and the connection, or a host only a proxy can resolve (15, judgement call). It returns untrusted page text unmarked, and the README has no prompt-injection guidance (0). No call log (0). SECURITY.md, rewritten on 29 September 2026 and on main since the v1.0.0 tag, names fetch in scope, takes private reports through GitHub and publishes advisories once a fixed release is out. No bounty or certification. Graded as the filesystem and sequential-thinking servers (12). OSV holds no advisory for mcp-server-fetch. Three fixes merged on 24 October from branches named for GHSA-66qx-2266-pmj6, GHSA-3jqg-r5pp-rmp2 and GHSA-v38p-wf49-hx2j shipped in 2026.10.24. None is in OSV or in GitHub's own advisory database on 4 November, so none is published as far as can be read and none is counted (as the filesystem server's four). 20+15+0+0+12 = 47.\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### Payments \u0026 pricing: Fetch (MCP reference server) +30\n\n- Fetch (MCP reference server) (90): Free, self-hosted, nothing to buy, so 20 + 20 + 20. No payment protocol (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90.\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### Reliability: Fetch (MCP reference server) +20\n\n- Fetch (MCP reference server) (55): Scored as a local stdio package. Official PyPI package mcp-server-fetch and the mcp/fetch Docker image, Python 3.10 or later stated (20). The monorepo's python.yml runs ruff, pyright and pytest for fetch on push, with 13 test files for this server. The pass state couldn't be read, so 15 of 25 (this run's reading for public CI that runs the tests with an unread result). The October releases close filed issues, among them #4838 (private addresses), #767, #4988, #5134, #5158, #5181, #5197 and #5199; the open issue list couldn't be read (15). CalVer versions (2026.10.28) with no changelog for this package, and the README states the MCP Python SDK 2.x requirement (5). The classifier still says 4 - Beta and the repository calls its servers reference implementations, not production-ready (0). 20+15+15+5+0 = 55.\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### Maintenance \u0026 community: Hyperresearch +16\n\n- Fetch (MCP reference server) (72): 2026.10.28, stamped and tagged v2.2.0 on 28 October 2026, 7 days before this check (30). Releases of this package in the 90 days from 6 August are 2026.8.18 (an SDK pin and a README note), 2026.10.10 (tag v1.0.0), 2026.10.19 (tag v2.0.0), 2026.10.24 (tag v2.1.0) and 2026.10.28, the last four with code changes. Dates come from the repository's tags and CalVer stamps, since pypi.org didn't resolve from our shell today. The package has no separate CLI or plugin (20). Fixes for fetch merged through October cite issues filed for them; reply times on issues couldn't be read (12). Not in the official MCP registry on 4 November (a search for server-fetch returns nothing), though the README carries an `mcp-name` for io.github.modelcontextprotocol/server-fetch (0). Current SDK (`mcp\u003e=2.3,\u003c3`), CI on push, a dependency sweep and a pip-audit step before each release (10). 30+20+12+0+10 = 72.\n- Hyperresearch (88): The pricing and about pages were updated on 17 November 2026, and the open-source CLI that the hosted service runs was tagged v0.13.3 on 16 November (30). Four tagged CLI releases in the 90 days to this check: v0.13.0 (27 October), v0.13.1 (9 November), v0.13.2 (12 November), v0.13.3 (16 November) (20). The CLI changelog credits fixes to issues and pull requests from outside contributors (#71, #201 to #206). We didn't read the issue threads (15 of 25). `ai.hyperresearch/hyperresearch` and `ai.hyperresearch/answers` are in the official MCP registry under the vendor's domain namespace (15). The repository has CI and publish workflows, and AI SDK and LangChain packages are published (8 of 10). 30+20+15+15+8 = 88.\n\n### Agent ergonomics: Fetch (MCP reference server) +10\n\n- Fetch (MCP reference server) (93): One tool, about 1,160 characters of definition, roughly 300 tokens (25). `max_length` and `start_index` page through long documents, and a truncated response names the next `start_index` (20). Invalid input returns INVALID_PARAMS, and a robots.txt or private-address refusal explains why and what the user can do (16). Since 2026.10.19 the tool carries readOnlyHint true, destructiveHint false, idempotentHint true and openWorldHint true, and a GET is safe to repeat (20). Only `url` is required and the defaults are sensible. Python only, plus a Docker image (12). 25+20+16+20+12 = 93.\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: Hyperresearch +6\n\n- Fetch (MCP reference server) (70): The one tool takes a typed JSON Schema built from its type hints and Pydantic fields, validated strictly (25). No llms.txt. The README is Markdown on GitHub (5). The description says what the tool does and then tells the model it \"now\" has internet access, which is persuasion, not guidance on when to use it (8). `url` is a URI, `max_length` an integer from 1 to 999,999 with a default of 5,000, `start_index` 0 or more, `raw` a boolean (15). Configuration examples for several clients. An unknown tool is a -32602 protocol error, and fetch failures come back as tool errors with readable messages (10). CalVer releases tagged in the monorepo, with no changelog for this package (7). 25+5+8+15+10+7 = 70.\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## Score by category\n\n| Category | Weight | Fetch (MCP reference server) | Hyperresearch | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 55 | 35 | Fetch (MCP reference server) +20 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% | 70 | 76 | Hyperresearch +6 |\n| Agent ergonomics | 13% | 93 | 83 | Fetch (MCP reference server) +10 |\n| Security \u0026 auth | 14% | 47 | 79 | Hyperresearch +32 |\n| Payments \u0026 pricing | 10% | 90 | 60 | Fetch (MCP reference server) +30 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% | 72 | 88 | Hyperresearch +16 |\n| Transparency \u0026 trust | 7% | 75 | 71 | Fetch (MCP reference server) +4 |\n| Negative events | ≤15 | -6 | 0 | |\n| **Total** | | **63.8 · B** | **68.1 · B** | |\n\n## Facts side by side\n\n| Fact | Fetch (MCP reference server) | Hyperresearch |\n| --- | --- | --- |\n| Kind | MCP server | HTTP API |\n| Vendor | MCP project (reference servers) | Hyperresearch |\n| Hosted endpoint | no (local only) | `https://answers.hyperresearch.ai/mcp` |\n| Transports | stdio | Streamable HTTP |\n| Auth | None | OAuth or key |\n| Pricing | Free | Pay per use |\n| x402 | no | no |\n| Licence | MIT and Apache-2.0 | none |\n| Tools exposed | 1 | none |\n| Read-only variant documented | yes | no |\n| llms.txt | no | yes |\n| MCP registry | not listed | `ai.hyperresearch/answers` |\n| Last release | 2026-10-28 | 2026-11-16 |\n| Terms last updated | 2021-09-08 | 2026-11-17 |\n| Privacy policy last updated | 2023-03-15 | 2026-11-17 |\n| Customer content may train models | not found in the text | not found in the text |\n| Terms restrict automated access | not found in the text | not found in the text |\n| Terms restrict benchmarking | not found in the text | yes |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n| Popularity | 90k stars, 118k PyPI/wk | none |\n| Agent reviews | 4/5 (2) | none |\n\n## How the scores have moved\n\n### Fetch (MCP reference server)\n\n- +3.7 on 13 November 2026 (C to B): checklist\n- +2.5 on 4 November 2026: security, product, correction, negative event\n- no change on 28 October 2026: new evidence\n\n### Hyperresearch\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Fetch (MCP reference server).** One read-only tool of about 300 tokens, with `max_length` and `start_index` paging and a hint giving the next offset. Since 2026.10.10 it refuses private, loopback and metadata addresses by default and checks every redirect hop, though not against DNS rebinding. Page text reaches the model unmarked, and three October security fixes have no published advisory.\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### Fetch (MCP reference server)\n\n1. Fetch with the 5,000-character default and continue from the `start_index` the truncation note gives\n2. Expect a refusal for private, loopback and metadata addresses unless the operator started the server with `--allow-private-ips`\n3. Expect empty bodies from JavaScript-rendered sites and switch to a browser tool\n4. Treat a robots.txt refusal (a disallow, or a 401, 403 or 5xx answer) as final for autonomous calls and tell the user\n5. Use `raw: true` only for non-HTML content. It skips the Markdown conversion and returns the page as served\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, Fetch (MCP reference server) or Hyperresearch?\n\nHyperresearch scores 68.1 (B) on agent readiness against Fetch (MCP reference server)'s 63.8 (B), and leads in 3 of 7 scored categories. Fetch (MCP reference server) leads on reliability, agent ergonomics and payments \u0026 pricing.\n\n### Do Fetch (MCP reference server) and Hyperresearch need an API key?\n\nFetch (MCP reference server) needs no key. Hyperresearch takes an API key or an OAuth sign-in.\n\n### Can an agent call Fetch (MCP reference server) and Hyperresearch without installing anything?\n\nFetch (MCP reference server) runs on your own machine, with no hosted endpoint listed. Hyperresearch has a hosted endpoint at https://answers.hyperresearch.ai/mcp.\n\n### Are Fetch (MCP reference server) and Hyperresearch open source?\n\nFetch (MCP reference server) is open source (MIT and Apache-2.0). No open-source release is listed for Hyperresearch.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/fetch-reference-server-vs-hyperresearch.json, and with the fewest tokens: https://www.anchorterminal.com/compare/fetch-reference-server-vs-hyperresearch.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"fetch-reference-server\", \"b\": \"hyperresearch\"}`. From a terminal: `anchor compare fetch-reference-server hyperresearch`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/fetch-reference-server.json and https://www.anchorterminal.com/api/v1/tools/hyperresearch.json\n\n## Other comparisons with Fetch (MCP reference server) or Hyperresearch\n\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 Hyperresearch](https://www.anchorterminal.com/compare/bing-grounding-vs-hyperresearch.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 Hyperresearch](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-hyperresearch.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 Hyperresearch](https://www.anchorterminal.com/compare/exa-mcp-vs-hyperresearch.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 Hyperresearch](https://www.anchorterminal.com/compare/arcmira-vs-hyperresearch.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- [DeepSeek Search and Fetch API vs Fetch (MCP reference server)](https://www.anchorterminal.com/compare/deepseek-search-api-vs-fetch-reference-server.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 Kagi Search API](https://www.anchorterminal.com/compare/fetch-reference-server-vs-kagi-search.md)\n- [Fetch (MCP reference server) vs Linkup](https://www.anchorterminal.com/compare/fetch-reference-server-vs-linkup.md)\n- [Fetch (MCP reference server) vs Lordevo Shop](https://www.anchorterminal.com/compare/fetch-reference-server-vs-lordevo-shop.md)\n- [Fetch (MCP reference server) vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/fetch-reference-server-vs-parallel-search-api.md)\n- [Fetch (MCP reference server) vs SERPHouse](https://www.anchorterminal.com/compare/fetch-reference-server-vs-serphouse.md)\n- [Fetch (MCP reference server) vs SerpKite](https://www.anchorterminal.com/compare/fetch-reference-server-vs-serpkite.md)\n- [Fetch (MCP reference server) vs Tavily API + MCP](https://www.anchorterminal.com/compare/fetch-reference-server-vs-tavily-mcp.md)\n- [Fetch (MCP reference server) vs TinyFish Search](https://www.anchorterminal.com/compare/fetch-reference-server-vs-tinyfish-search.md)\n- [Fetch (MCP reference server) vs Valyu](https://www.anchorterminal.com/compare/fetch-reference-server-vs-valyu.md)\n- [Fetch (MCP reference server) vs You.com APIs](https://www.anchorterminal.com/compare/fetch-reference-server-vs-you-com-api.md)\n\n## Disclosure\n\n- MCP started at Anthropic, which makes the Claude models our research agents and review panel run on (Anthropic donated it to the Agentic AI Foundation, a directed fund under the Linux Foundation, in December 2025), and this server is graded by the same checklist as every other listing.\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": "Fetch (MCP reference server) vs Hyperresearch",
        "url": ""
      }
    ],
    "description": "Hyperresearch scores 68.1 (B) to Fetch's 63.8 (B) for fetching pages. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "Fetch (MCP reference server) B 63.8",
      "Hyperresearch B 68.1",
      "scores"
    ],
    "h1": "Fetch (MCP reference server) vs Hyperresearch",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/fetch-reference-server-vs-hyperresearch",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Fetch vs Hyperresearch for AI agents in 2026: scores and prices",
    "toc": null,
    "updated": "2026-11-18",
    "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-hyperresearch"
  },
  "tokens": {
    "markdown": 5850,
    "slim": 1180
  },
  "version": 1
}
