{
  "data": {
    "a": {
      "slug": "serpkite",
      "name": "SerpKite",
      "vendor": "SerpKite (Anastasia Klimova, trading as SerpKite)",
      "vendorUrl": "https://serpkite.com",
      "kind": "http-api",
      "category": "search",
      "summary": "Google SERP API for AI agents from SerpKite, a sole trader in Ontario. It returns Google results, other verticals and public AI assistant answers as JSON or Markdown, fetches pages, and runs a remote MCP server with 23 tools.",
      "url": "https://www.anchorterminal.com/tools/serpkite",
      "markdownUrl": "https://www.anchorterminal.com/tools/serpkite.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/serpkite.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/serpkite.json",
      "dns": "serpkite.grade.anchorterminal.com",
      "repo": "https://github.com/SerpKite/serpkite-mcp",
      "license": "Proprietary service under SerpKite's terms of service. The SDKs (TypeScript, Python, Go, LangChain, Vercel AI SDK) and the MCP connection repository on GitHub are MIT",
      "transports": [
        "http",
        "streamable-http"
      ],
      "remoteUrl": "https://api.serpkite.com/v1/search",
      "packages": [
        {
          "registry": "npm",
          "name": "serpkite"
        },
        {
          "registry": "pypi",
          "name": "serpkite"
        },
        {
          "registry": "go",
          "name": "github.com/serpkite/serpkite-go"
        }
      ],
      "auth": "api-key",
      "authNotes": "API key (`skt_live_…`) as `Authorization: Bearer` on every REST call and on the remote MCP server; since 9 October 2026 the bare key without `Bearer` is accepted too. GET requests may also send it as the `?api_key=` query parameter. An account can hold many keys, each revocable and rotatable with an optional monthly credit limit, and keys are stored as SHA-256 hashes. No scopes. Since 9 October the MCP server also supports OAuth (authorisation code with PKCE, dynamic client registration, rotating refresh tokens); an approved connection runs as a named API key and its token works on /v1/mcp only (https://serpkite.com/docs/mcp, https://serpkite.com/docs/changelog).",
      "pricing": "freemium",
      "pricingNotes": "Prepaid credit packs that never expire. Starter $10 for 10,000 credits ($1.00 per 1,000), Growth $50 for 62,500 ($0.80), Pro $300 for 500,000 ($0.60), volume quotes from $0.18 per 1,000 at 25 million a month. One credit is one page of 10 results; `num=100` is 7 credits, autocomplete 0.5, batch and cache hits half price, `include_content` 1 per fetched page, AI assistant answers 2 to 4 credits. Free credits with no card (1,000 on email verification, 1,500 more after linking GitHub or Google) and 1,000 a month, with a free daily limit of 500 credits; since 28 October free credits are paused for an account sharing a device or network with another. Batch depth requests move to per-page billing on 23 November 2026. Failed, empty and blocked requests are refunded. Paddle is the merchant of record (https://serpkite.com/pricing, checked 2026-11-02).",
      "priceSummary": "$1 / 1k req",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in llms.txt, the OpenAPI spec or the pricing page. Packs are bought through Paddle checkout (checked 2026-10-05).",
        "endpoints": []
      },
      "toolCount": 23,
      "popularity": {
        "githubStars": null,
        "npmWeekly": 809,
        "pypiWeekly": 376,
        "asOf": "2026-10-05"
      },
      "docsUrl": "https://serpkite.com/docs",
      "llmsTxt": "https://serpkite.com/llms.txt",
      "openapi": "https://serpkite.com/openapi/serp-api.yaml",
      "registryName": "io.github.SerpKite/serpkite",
      "capabilities": [
        "web.search",
        "search.serp",
        "search.news",
        "search.images",
        "web.fetch",
        "web.extract",
        "web.crawl"
      ],
      "tags": [
        "hosted",
        "freemium",
        "no-card",
        "free-tier",
        "closed-source",
        "mcp",
        "openapi",
        "llms-txt",
        "typescript",
        "python",
        "go",
        "status-page"
      ],
      "lastRelease": "2026-11-01",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 67.6,
        "grade": "B",
        "agentReady": false,
        "rank": 274,
        "ranked": true,
        "rankOf": 1272,
        "categoryRank": 8,
        "methodology": "0.7",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 97,
          "maintenance": 80,
          "payments": 40,
          "reliability": 75,
          "schema": 90,
          "security": 37,
          "transparency": 77
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-02"
        },
        "negative": -3,
        "negativeNotes": [
          "2 October to 1 November 2026. The `ai_overview` parameter and field, the `/v1/ai-mode` endpoint and its MCP tool, and the `/v1/lens` endpoint were removed the day each removal was announced (2 and 3 October), three to four days after the v1.0.0 changelog listed AI Overview as unchanged, with Google's refusal of logged-out requests as the reason. Later same-day changes fold into this term, among them `/v1/reviews` answering 400 for sorts other than `most_relevant` and stopping at review 10 (16 October), and `page: 2` and later answering 503 instead of an empty result (1 November). AI Overview and AI Mode came back on 28 October. Folded into one small deduction, -3 (https://serpkite.com/docs/changelog)."
        ],
        "verdict": "Google SERP API with an OpenAPI 3.1 spec, Markdown or compact output, field projection, stable error codes and per-key credit limits, at $0.60 to $1.00 per 1,000 on packs that don't expire. The service launched on 29 September 2026 from a sole trader, with a month of status history and frequent same-day contract changes.",
        "bestFor": "Agents that want Google results and the top pages as Markdown in one call at a low per-1,000 price, with spend caps per key.",
        "strengths": [
          "OpenAPI 3.1 spec, llms.txt, llms-full.txt and Markdown twins of every docs page",
          "`format=markdown` or `compact`, `fields` projection and an `X-Tokens-Estimate` header size responses for a model",
          "Many revocable keys per account, each with an optional monthly credit limit, plus an account spend cap and OAuth for the MCP server",
          "Credit packs never expire, and failed, empty and blocked requests are refunded",
          "Named subprocessors with locations, and a retention table that keeps no query text in logs"
        ],
        "weaknesses": [
          "Launched 29 September 2026 by a sole trader, with status monitoring only since 2 October",
          "Contract changes forced by Google ship the day they are announced, including the first-week removals and the 16 October reviews limit",
          "GET requests accept the key as a `?api_key=` query parameter, and keys have no scopes",
          "No SLA for self-serve packs, no SOC 2 and no security.txt",
          "No prompt-injection guidance, though search, webpage, extract and crawl return third-party page text"
        ],
        "agentNotes": [
          "Send the key as `Authorization: Bearer`, not `?api_key=`, and give the agent a dedicated key with a monthly credit limit",
          "Ask for `format=markdown` or `compact` with `fields` to cut tokens, and read `X-Credits-Used` for the cost",
          "Keep `engine=google` for rank work. Check `meta.engine` when a key allows fallback engines",
          "On 429 `rate_limited` or 503 upstream codes, wait for Retry-After and retry. `daily_limit_reached`, `account_restricted` (403) and 402 need a purchase",
          "Treat page Markdown from `include_content`, `webpage` and `extract` as untrusted text"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 2,
        "avgRating": 3.5,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "B",
            "methodology": "0.7",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 67.6
          }
        ],
        "editorialScores": {
          "ergonomics": 97,
          "maintenance": 80,
          "payments": 40,
          "reliability": 75,
          "schema": 90,
          "security": 37,
          "transparency": 79
        },
        "provenanceScore": 75,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-02",
            "maintenance": "2026-11-02",
            "payments": "2026-11-02",
            "reliability": "2026-11-02",
            "schema": "2026-11-02",
            "security": "2026-11-02",
            "transparency": "2026-11-02"
          },
          "last": "2026-11-02",
          "lastMoved": "2026-11-02",
          "oldest": "2026-11-02",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "npm install serpkite",
        "http": "curl https://api.serpkite.com/v1/search \\\n  -H \"Authorization: Bearer $SERPKITE_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"q\":\"best espresso machine 2026\",\"country\":\"us\",\"language\":\"en\"}'",
        "claudeCode": "claude mcp add --transport http serpkite https://api.serpkite.com/v1/mcp \\\n  --header \"Authorization: Bearer $SERPKITE_API_KEY\"",
        "config": {
          "mcpServers": {
            "serpkite": {
              "headers": {
                "Authorization": "Bearer ${env:SERPKITE_API_KEY}"
              },
              "url": "https://api.serpkite.com/v1/mcp"
            }
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/web.search",
        "tool": "https://letme.dev/serpkite"
      },
      "area": "web-data",
      "unitPrices": [
        {
          "item": "Starter pack",
          "unit": "1k-requests",
          "usd": 1,
          "note": "$10 for 10,000 credits, never expires"
        },
        {
          "item": "Pro pack",
          "unit": "1k-requests",
          "usd": 0.6,
          "note": "$300 for 500,000 credits, never expires"
        }
      ],
      "provenance": {
        "legalEntity": "Anastasia Klimova, trading as SerpKite",
        "domain": "serpkite.com",
        "domainRegistered": "2026-09-29",
        "endpointOnVendorDomain": true,
        "terms": "https://serpkite.com/legal/terms",
        "privacy": "https://serpkite.com/legal/privacy",
        "statusPage": "https://status.serpkite.com",
        "changelog": "https://serpkite.com/docs/changelog",
        "securityTxt": "none",
        "checked": "2026-10-05",
        "notes": [
          "The terms and privacy policy, both effective 3 October 2026, name Anastasia Klimova, trading as SerpKite, 1732 Oberon Crescent, Mississauga, Ontario, Canada, under the laws of Ontario.",
          "RDAP for serpkite.com gives a registration date of 2026-09-29 and Cloudflare, Inc. as registrar.",
          "serpkite.com/.well-known/security.txt returns the site's 404 page. The security page asks for reports by email with acknowledgement in 2 business days and says there's no paid bug bounty.",
          "The MCP registry entry uses the GitHub namespace io.github.SerpKite, not a domain-verified one. The repository's two commits are by the GitHub user nolikzero, and the SDK repositories are committed by serpkite-bot \u003csupport@serpkite.com\u003e.",
          "The subprocessor page lists Polar as merchant of record for earlier orders, which suggests sales before the domain's registration date. We couldn't establish where."
        ],
        "score": 75
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/serpkite.json",
      "live": {
        "slug": "serpkite",
        "probe": {
          "target": "https://api.serpkite.com/v1/search",
          "method": "get",
          "lastAt": "2026-11-03T18:20:21.65941807Z",
          "lastOk": true,
          "lastStatus": 401,
          "lastMs": 129,
          "lastNote": "asks for credentials",
          "authRequired": true,
          "uptime24h": 97.2,
          "uptime30d": 99.88,
          "p50ms24h": 132,
          "p95ms24h": 204,
          "samples24h": 250,
          "samples30d": 7264,
          "days": [
            {
              "date": "2026-10-06",
              "probes": 270,
              "ok": 270
            },
            {
              "date": "2026-10-07",
              "probes": 272,
              "ok": 272
            },
            {
              "date": "2026-10-08",
              "probes": 268,
              "ok": 268
            },
            {
              "date": "2026-10-09",
              "probes": 250,
              "ok": 250
            },
            {
              "date": "2026-10-10",
              "probes": 247,
              "ok": 247
            },
            {
              "date": "2026-10-11",
              "probes": 247,
              "ok": 247
            },
            {
              "date": "2026-10-12",
              "probes": 247,
              "ok": 247
            },
            {
              "date": "2026-10-13",
              "probes": 248,
              "ok": 248
            },
            {
              "date": "2026-10-14",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-10-15",
              "probes": 253,
              "ok": 253
            },
            {
              "date": "2026-10-16",
              "probes": 252,
              "ok": 252
            },
            {
              "date": "2026-10-17",
              "probes": 253,
              "ok": 253
            },
            {
              "date": "2026-10-18",
              "probes": 256,
              "ok": 256
            },
            {
              "date": "2026-10-19",
              "probes": 255,
              "ok": 253
            },
            {
              "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": 250,
              "ok": 250
            },
            {
              "date": "2026-10-29",
              "probes": 249,
              "ok": 249
            },
            {
              "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": 191,
              "ok": 184
            }
          ],
          "outages": [
            {
              "start": "2026-11-03T10:35:09.387488166Z",
              "end": "2026-11-03T11:14:41.456082867Z",
              "note": "HTTP 530 server error"
            }
          ]
        },
        "vendorStatus": {
          "page": "https://status.serpkite.com",
          "indicator": "unknown",
          "summary": "no machine-readable status found",
          "checkedAt": "2026-11-03T17:13:39.502363141Z"
        },
        "versions": [
          {
            "registry": "mcp-registry",
            "name": "io.github.SerpKite/serpkite",
            "version": "1.2.0",
            "seenAt": "2026-11-03T16:51:07.971176756Z"
          },
          {
            "registry": "npm",
            "name": "serpkite",
            "version": "0.8.2",
            "seenAt": "2026-11-02T19:50:20.979998437Z"
          },
          {
            "registry": "pypi",
            "name": "serpkite",
            "version": "0.8.2",
            "released": "2026-10-28",
            "seenAt": "2026-11-02T19:50:22.823850823Z"
          }
        ],
        "githubStars": 0,
        "npmWeekly": 582,
        "pypiWeekly": 405,
        "securityTxt": {
          "url": "https://serpkite.com/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-11-03T15:51:31.90054891Z"
        },
        "llmsTxt": {
          "url": "https://serpkite.com/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-11-03T15:21:06.283815677Z"
        },
        "domain": {
          "domain": "serpkite.com",
          "registered": "2026-09-29",
          "source": "https://rdap.verisign.com/com/v1/domain/serpkite.com",
          "checkedAt": "2026-11-01T14:17:34.283329903Z"
        },
        "pages": [
          {
            "url": "https://serpkite.com/docs/changelog",
            "kind": "changelog",
            "status": 200,
            "checkedAt": "2026-11-03T07:58:29.614448003Z",
            "changedAt": "2026-11-02T07:25:21.769205834Z",
            "fingerprint": "34aaf3fcb016"
          },
          {
            "url": "https://serpkite.com/pricing",
            "kind": "pricing",
            "status": 200,
            "checkedAt": "2026-11-03T07:58:35.706697239Z",
            "changedAt": "2026-10-30T05:48:24.293981147Z",
            "fingerprint": "bda620bd0b87"
          },
          {
            "url": "https://serpkite.com/legal/privacy",
            "kind": "privacy",
            "status": 200,
            "checkedAt": "2026-11-03T07:58:31.938693926Z",
            "changedAt": "2026-10-30T05:48:20.283333336Z",
            "fingerprint": "dcf79e062721"
          },
          {
            "url": "https://serpkite.com/legal/terms",
            "kind": "terms",
            "status": 200,
            "checkedAt": "2026-11-03T07:58:33.6934251Z",
            "changedAt": "2026-10-30T05:48:22.292247303Z",
            "fingerprint": "3c97025fee76"
          }
        ],
        "github": {
          "repo": "serpkite/serpkite-mcp",
          "checkedAt": "2026-11-02T09:24:51.977048937Z",
          "stars": 0,
          "archived": false,
          "issuesEnabled": true,
          "pushedAt": "2026-10-28T22:42:28Z",
          "openIssues": 0,
          "openPRs": 0,
          "issuesOpened90d": 0,
          "issuesClosed90d": 0,
          "prsMerged90d": 5
        },
        "updatedAt": "2026-11-03T18:20:21.65941807Z"
      }
    },
    "answer": "SerpKite scores 67.6 (B) on agent readiness against SpecStream's 64.4 (B), and leads in 4 of 7 scored categories. SpecStream leads on security \u0026 auth and payments \u0026 pricing.",
    "b": {
      "slug": "specstream",
      "name": "SpecStream",
      "vendor": "SpecStream SAS",
      "vendorUrl": "https://specstream.ai",
      "kind": "platform",
      "category": "search",
      "summary": "SpecStream is a hosted web data service that turns a plain-language request into rows with a source page for each value, enriches and rechecks lists, and is reached through a web app, REST API, SDKs and remote MCP server.",
      "url": "https://www.anchorterminal.com/tools/specstream",
      "markdownUrl": "https://www.anchorterminal.com/tools/specstream.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/specstream.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/specstream.json",
      "dns": "specstream.grade.anchorterminal.com",
      "repo": "https://github.com/specstream/specstream-tools",
      "license": "Proprietary hosted service under SpecStream SAS's terms of use (updated 3 November 2026, French law). The client code in specstream/specstream-tools (SDKs, the stdio bridge, framework packages, plugins, skills and integrations) is MIT, copyright SpecStream SAS",
      "transports": [
        "streamable-http",
        "http"
      ],
      "remoteUrl": "https://api.specstream.ai/mcp",
      "packages": [
        {
          "registry": "pypi",
          "name": "specstream-client"
        },
        {
          "registry": "npm",
          "name": "@specstream/sdk"
        },
        {
          "registry": "pypi",
          "name": "specstream-mcp-stdio"
        }
      ],
      "auth": "mixed",
      "authNotes": "Two credentials, both sent as `Authorization: Bearer`. API keys (`ss_live_...`) are made under Agents \u0026 API in the workspace or with the `create_api_key` tool, shown once, limited to any of eight scopes (`specs:read`, `specs:write`, `finds:read`, `finds:write`, `finds:spend`, `projects:read`, `projects:manage`, `account:read`), to named projects, to an expiry of 1 to 365 days (90 by default) and to a spending ceiling, and revoked singly so that the next request fails; the docs group them as read, prepare or execute access and only execute starts paid work. OAuth 2.1 sign-in for MCP clients uses HTTPS client ID metadata documents or dynamic client registration, with read, prepare or execute access shown on a consent screen, and registered clients are listed and revoked in account settings. Delegated access can let an agent start named operations within a per-run limit, a monthly limit and an expiry. No secret in a query string is documented. The authorisation server metadata on api.specstream.ai was not read (see openQuestions).",
      "pricing": "usage",
      "pricingNotes": "Prices are per matching result and the same on every plan, Standard $0.05 (up to 5 facts), Expanded $0.15 (up to 15 facts and one related list with 10 related records, then 10 cents per further 10), Deep $1, plus 5 cents for a named person's email and 15 cents for a phone. Rechecks cost half the rate for a changed or new row and 1 cent for an unchanged one; checking an imported row costs 5 cents or its match rate. A run that finds nothing, rows left out and reading or pricing a request cost nothing. Free is $10 of work once for the first 30 days with no card; pay as you go tops up from $10 with no expiry; Pro $19 a month with $19 of work, Scale $99, Team $499, Enterprise from $2,500; yearly adds 20 per cent more work, and plan balance rolls over one month. Agents without an account can pay per purchase by x402 (USDC) or MPP (card, at least $1) (https://specstream.ai/pricing and https://specstream.ai/docs/agent-payments, checked 2026-11-03).",
      "priceSummary": "$19 / mo",
      "where": "hosted",
      "x402": {
        "level": "yes",
        "evidence": "The agent payments page documents `POST https://api.specstream.ai/v1/agent/lists` as the one paid route for agents without an account. It answers 402 with a `PAYMENT-REQUIRED` header for x402 v2 (USDC on Base, Arbitrum or Polygon, a Permit2 authorisation for the quoted maximum under the `upto` scheme, settled for the results cost only) and a `WWW-Authenticate: Payment` challenge for MPP by card through Stripe's Link agent wallet; the offer lasts 15 minutes and a purchase is 1 to 500 results for $1.00 to $500.00. Pricing and the changelog (15 October 2026) say the same. Not exercised, because api.specstream.ai's robots.txt could not be read, so nothing on that host was requested (https://specstream.ai/docs/agent-payments, checked 2026-11-03).",
        "endpoints": [
          {
            "url": "https://api.specstream.ai/v1/agent/lists",
            "priceUsd": null,
            "network": "eip155:8453"
          },
          {
            "url": "https://api.specstream.ai/v1/agent/lists",
            "priceUsd": null,
            "network": "eip155:42161"
          },
          {
            "url": "https://api.specstream.ai/v1/agent/lists",
            "priceUsd": null,
            "network": "eip155:137"
          }
        ]
      },
      "toolCount": 128,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-03"
      },
      "docsUrl": "https://specstream.ai/docs",
      "llmsTxt": "https://specstream.ai/llms.txt",
      "openapi": "https://specstream.ai/openapi.json",
      "registryName": "ai.specstream/specstream",
      "capabilities": [
        "search.research",
        "web.search",
        "web.extract",
        "lead.enrichment",
        "data.company",
        "email.finder"
      ],
      "tags": [
        "hosted",
        "official",
        "closed-source",
        "openapi",
        "llms-txt",
        "mcp",
        "remote-mcp",
        "oauth",
        "api-key",
        "x402",
        "mpp",
        "a2a",
        "python",
        "typescript",
        "cli",
        "webhooks",
        "async-jobs",
        "agent-skills",
        "enrichment",
        "desktop-app",
        "windows",
        "eu-hosting",
        "usage-based",
        "free-tier",
        "no-card",
        "no-status-page",
        "new"
      ],
      "lastRelease": "2026-11-03",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 64.4,
        "grade": "B",
        "agentReady": false,
        "rank": 399,
        "ranked": true,
        "rankOf": 1272,
        "categoryRank": 11,
        "methodology": "0.7",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 65,
          "maintenance": 81,
          "payments": 85,
          "reliability": 23,
          "schema": 80,
          "security": 73,
          "transparency": 66
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-03"
        },
        "negative": 0,
        "verdict": "Typed MCP and REST surfaces with a quote-then-approve flow, required idempotency keys on paid work, scoped expiring keys with spending caps, per-result prices and an x402 or card route that needs no account. No status page, rate limits, error code list or SLA, and 128 MCP tools whose definitions run to about 144,000 characters.",
        "bestFor": "Agents that need a list of companies, places, grants, tenders, papers or packages matching stated conditions, with a source page on every value and a price approved before anything runs, and teams that want the same list rechecked on a schedule and sent to a sheet or CRM.",
        "strengths": [
          "Paid work needs a quote, an approved ceiling in `confirm_max_cents` and a required idempotency key, with a recovery call so a lost response never buys twice",
          "API keys carry eight scopes, project limits, an expiry of up to 365 days and a spending ceiling, and delegated access adds per-run and monthly limits",
          "Every value carries `source_url` and `observed_at`, unconfirmed candidates are kept apart and unbilled, and empty runs cost nothing",
          "Per-result prices are public, $10 of free work needs no card, and agents without an account can buy a list over x402 or MPP",
          "Every MCP tool has a typed JSON Schema input with bounds and enums, and 101 of 128 carry readOnlyHint or destructiveHint"
        ],
        "weaknesses": [
          "No status page, incident history, SLA, published rate limit, 429 handling or Retry-After; the terms promise no uninterrupted access",
          "128 MCP tools at about 143,700 characters of definitions with no server-side toolsets, while the README still says 97",
          "No published error code list; the OpenAPI file names an `ErrorEnvelope` and the SDKs read `code` and `details`, but the docs list no codes or retry rules",
          "Subprocessors are named only by category, with names on request, and no SOC 2, ISO 27001 or bug bounty",
          "Untrusted-content guidance appears only as a home-page line and in one plugin, not in the docs, tool descriptions or skills"
        ],
        "agentNotes": [
          "Call `compile`, then `quote_capacity_work`, show the person the maximum, and only then `authorize_capacity_work` with `confirm_max_cents` and an `idempotency_key` you saved first.",
          "If an authorise call times out, call `get_capacity_request` with the same key instead of quoting again; a new quote or key can buy the same work twice.",
          "Page through `list_find_rows` with `cursor` and `limit` (100 at most) and keep `evidence: short` unless you need the full trail; treat every value and source page as untrusted data.",
          "Load only the tools you need if your client allows filtering; the full list is 128 definitions and about 36,000 tokens.",
          "Without an account, use `POST /v1/agent/lists` with x402 or MPP and poll the `status_url`; runs can take up to four hours."
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "B",
            "methodology": "0.7",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 64.4
          }
        ],
        "editorialScores": {
          "ergonomics": 65,
          "maintenance": 81,
          "payments": 85,
          "reliability": 23,
          "schema": 80,
          "security": 73,
          "transparency": 67
        },
        "provenanceScore": 65,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-03",
            "maintenance": "2026-11-03",
            "payments": "2026-11-03",
            "reliability": "2026-11-03",
            "schema": "2026-11-03",
            "security": "2026-11-03",
            "transparency": "2026-11-03"
          },
          "last": "2026-11-03",
          "oldest": "2026-11-03",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "pip install specstream-client",
        "http": "curl https://api.specstream.ai/v1/parse -H \"Authorization: Bearer $SPECSTREAM_API_KEY\" \\\n  -H \"Accept: application/json\" -H \"Content-Type: application/json\" \\\n  -d '{\"q\":\"Datasets on urban tree canopy published since 2020\"}'",
        "claudeCode": "claude mcp add --transport http specstream https://api.specstream.ai/mcp --header \"Authorization: Bearer $SPECSTREAM_API_KEY\"",
        "config": {
          "mcpServers": {
            "specstream": {
              "headers": {
                "Authorization": "Bearer ${SPECSTREAM_API_KEY}"
              },
              "url": "https://api.specstream.ai/mcp"
            }
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/search.research",
        "tool": "https://letme.dev/specstream"
      },
      "area": "web-data",
      "unitPrices": [
        {
          "item": "Standard result (up to 5 facts)",
          "unit": "record",
          "usd": 0.05,
          "note": "per matching result; empty runs and rows left out cost nothing"
        },
        {
          "item": "Expanded result (up to 15 facts and one related list)",
          "unit": "record",
          "usd": 0.15,
          "note": "includes 10 related records, then $0.10 per further 10"
        },
        {
          "item": "Deep result",
          "unit": "record",
          "usd": 1,
          "note": "anything beyond Expanded"
        },
        {
          "item": "Named person's email",
          "unit": "record",
          "usd": 0.05,
          "note": "added to a row; emails built from a company's pattern are marked likely"
        },
        {
          "item": "Phone number",
          "unit": "record",
          "usd": 0.15,
          "note": "added to a row"
        },
        {
          "item": "Recheck of an unchanged row",
          "unit": "record",
          "usd": 0.01,
          "note": "changed or new rows cost half their rate (3, 8 or 50 cents)"
        },
        {
          "item": "Pro plan",
          "unit": "month",
          "usd": 19,
          "note": "$19 of work a month, 1 member, 10 lists kept current"
        },
        {
          "item": "Scale plan",
          "unit": "month",
          "usd": 99,
          "note": "$99 of work a month, 10 members, 50 lists"
        },
        {
          "item": "Team plan",
          "unit": "month",
          "usd": 499,
          "note": "$499 of work a month, 50 members, 250 lists"
        }
      ],
      "provenance": {
        "legalEntity": "SpecStream SAS",
        "domain": "specstream.ai",
        "domainRegistered": "",
        "endpointOnVendorDomain": true,
        "terms": "https://specstream.ai/terms",
        "privacy": "https://specstream.ai/privacy",
        "statusPage": "",
        "changelog": "https://specstream.ai/changelog",
        "securityTxt": "valid",
        "checked": "2026-11-03",
        "notes": [
          "The legal notice in English and French (both updated 3 November 2026) names SpecStream SAS, a French société par actions simplifiée with share capital of 10 euros, RCS Narbonne 131 125 841, VAT FR49131125841, registered at 20 quai de Lorraine, 11100 Narbonne, with Tarek Etman as president and publication director and Nataliia Stepanenko as director general, hosted by Compagnie IBM France SAS on IBM Cloud in Madrid. The terms and privacy policy (both 3 November 2026) name the same company under French law.",
          "The company number was not confirmed against the register. annuaire-entreprises.data.gouv.fr and recherche-entreprises.api.gouv.fr were refused by our fetcher and a web search found no register page. The SIREN 131125841 passes its Luhn check digit and the VAT key 49 matches it; SIREN numbers starting with 1 or 2 are normally given to public bodies, which a private SAS would not be. No first-hand page contradicts the notice, so nothing is deducted.",
          "https://specstream.ai/.well-known/security.txt is valid (Contact support@specstream.ai, Expires 2027-10-08, languages en and fr). The repository's SECURITY.md adds GitHub private vulnerability reporting.",
          "firstReleased is 2026-09-30, the first entry in the dated changelog (the Windows workspace app); the npm SDK and n8n node were first published on 12 October and the stdio bridge on 12 October 2026. lastRelease is 2026-11-03, specstream-mcp-stdio 1.2.3 on PyPI.",
          "robots.txt on specstream.ai allows / and disallows /workspace (except /workspace/shared/ and /workspace/assets/), /app/, /account, /login, /signup, /join, /v1/, /oauth/, /mcp, /share/, /export/, /internal/, /cdn-cgi/ and the paths under /integrations/*/, with no rule for named AI crawlers. api.specstream.ai/robots.txt could not be read, so nothing on that host was fetched, including the OAuth well-known documents, the A2A agent card and the MCP server card.",
          "Not read: RDAP for specstream.ai, the Wayback Machine, the live MCP registry entry, PyPI project pages (a client challenge; the release feed was read instead) and the GitHub API for stars and issues."
        ],
        "score": 65
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/specstream.json",
      "live": {
        "slug": "specstream",
        "probe": {
          "target": "https://api.specstream.ai/mcp",
          "method": "get",
          "lastAt": "2026-11-03T18:20:23.661096193Z",
          "lastOk": true,
          "lastStatus": 401,
          "lastMs": 228,
          "lastNote": "asks for credentials",
          "authRequired": true,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 198,
          "p95ms24h": 292,
          "samples24h": 44,
          "samples30d": 44,
          "days": [
            {
              "date": "2026-11-03",
              "probes": 44,
              "ok": 44
            }
          ]
        },
        "versions": [
          {
            "registry": "mcp-registry",
            "name": "ai.specstream/specstream",
            "version": "1.3.0",
            "seenAt": "2026-11-03T16:51:07.971176756Z"
          }
        ],
        "securityTxt": {
          "url": "https://specstream.ai/.well-known/security.txt",
          "state": "valid",
          "expires": "2027-10-08T00:00:00.000Z",
          "checkedAt": "2026-11-03T15:52:31.491866186Z"
        },
        "llmsTxt": {
          "url": "https://specstream.ai/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-11-03T15:21:10.521972292Z"
        },
        "updatedAt": "2026-11-03T18:20:23.661096193Z"
      }
    },
    "edges": [
      {
        "by": 52,
        "category": "reliability",
        "leads": "serpkite",
        "name": "Reliability",
        "reasons": {
          "a": "Hosted API, read with the hosted lines. Better Stack status page at status.serpkite.com with four monitors (api.serpkite.com/healthz, dashboard API, dashboard, website) and daily bars (20). Monitoring began on 2 October 2026, so the record covers 31 days of the 90 from 4 August. The page's own figures give 99.978 per cent uptime over 30 days for the API health monitor and 99.971 for the dashboard API, the 5 October check saw 29 to 41 minutes of downtime on each monitor on 2 October and 19 seconds on 3 October, and the feed has never carried an incident post. No outage reached an hour. A readable record shorter than 90 days with nothing major scores 15, as this run settled for short records. Rate limits published per key, 5 to 100 requests a second by pack (15). 429 `rate_limited` with Retry-After, backoff guidance for 429 and 503, and `Idempotency-Key` on batch creation (15). The terms say self-serve plans have no uptime guarantee and an enterprise SLA sits in a separate agreement we couldn't read (0). v1 API with no beta or preview label (10). 20+15+15+15+0+10 = 75.",
          "b": "Hosted reading, for the MCP server and REST API on api.specstream.ai. No public status page was found. None is linked from the site, llms.txt or the docs, llms-full.txt mentions none, and https://specstream.ai/status returned an error (0). No readable incident history, so the floor (5). No rate limit with numbers is published in the docs, llms.txt, llms-full.txt or the part of the OpenAPI file read; the privacy policy and DPA mention rate limiting without figures, and the published limits are per job (10,000 results a request, four-hour runs, 20,000 imported rows) (0). Nothing documents 429, Retry-After or backoff, but paid work requires an `idempotency_key` on `authorize_capacity_work` and `POST /v1/capacity/executions`, `GET /v1/capacity/requests/{request_key}` recovers the original find after an uncertain response, and the skills say never to quote again to recover a lost reply (8 of 15). No SLA on any plan, and the terms say 'We do not promise uninterrupted access' (0). No beta or preview label on the API, the MCP server or the SDKs, which PyPI classifies as production and stable at 1.2 (10). 0+5+0+8+0+10 = 23."
        },
        "scores": {
          "a": 75,
          "b": 23
        }
      },
      {
        "by": 45,
        "category": "payments",
        "leads": "specstream",
        "name": "Payments \u0026 pricing",
        "reasons": {
          "a": "No x402, MPP or L402 in llms.txt, the OpenAPI spec or the pricing page (0). Per-pack and per-credit prices published without a login, $1.00 to $0.60 per 1,000 (20). Free credits on signup and 1,000 a month with no card, per the quickstart and home page (20). A person signs in by email, GitHub or Google in a browser (0).",
          "b": "x402 v2 (USDC on Base, Arbitrum or Polygon, Permit2 `upto` for the quoted maximum, settled for the results cost) and MPP by card on SpecStream's own `POST /v1/agent/lists`, the route for buying a list of 1 to 500 results without an account; enrichment of imported lists, refreshes, monitors and investigations need an account, and the route was read in the docs and not exercised because api.specstream.ai's robots.txt could not be read, so partial (25). Per-result prices published without a login, 5, 15 or 100 cents a result, 5 cents an email, 15 cents a phone, rechecks at half rate or 1 cent (20). $10 of work for 30 days with no card (20). An agent can buy a list over x402 or MPP with no account, and the A2A endpoint prices a request without a key (20). 25+20+20+20 = 85."
        },
        "scores": {
          "a": 40,
          "b": 85
        }
      },
      {
        "by": 36,
        "category": "security",
        "leads": "specstream",
        "name": "Security \u0026 auth",
        "reasons": {
          "a": "Many keys per account, each revocable and rotatable with an optional monthly credit limit, stored as SHA-256 hashes, with no scopes. Since 9 October the MCP server also takes OAuth (authorisation code with PKCE, dynamic client registration, rotating refresh tokens, one `mcp` scope), each connection running as a named, revocable API key, while REST still needs a key (20). The docs allow the key as `?api_key=` on GET requests (minus 10). Search is read-only, and per-key limits and an account spend cap bound cost, but there's no read-only key, and the MCP server exposes crawl alongside search with no confirmation step we could see (10). Results include third-party snippets and full page Markdown, and we found no prompt-injection guidance (0). The dashboard request log keeps per-call metadata (endpoint, status, credits, key) for 31 days with CSV export, and each key records who created it (12). security.txt returns 404. The security page has a disclosure policy with acknowledgement in 2 business days, no paid bug bounty and SOC 2 marked as not yet started (5).",
          "b": "API keys `ss_live_...` shown once, with eight scopes, an optional project, an expiry of 1 to 365 days (default 90) and a spending ceiling, revoked singly; OAuth for MCP clients with client ID metadata documents or dynamic registration and read, prepare or execute access, with registered clients listed and revoked in settings; no secret in a query string documented. The authorisation server metadata on api.specstream.ai was not read and rotation is not described beyond expiry (28 of 30). Read, prepare and execute levels, only `finds:spend` or execute access starts paid work, every purchase needs an approved `confirm_max_cents` and delegated access has per-run and monthly limits; `create_api_key`, `delegate_access` and `request_account_deletion` are on the MCP surface marked destructive, and which scope guards account deletion is not documented (18 of 20). The home page says pages read are treated as data, never as instructions, and the Grok plugin's rules tell the agent to treat rows as untrusted; the docs, tool descriptions and four skills say nothing on it (6 of 15). A 12-month audit log of sign-ins, keys, delegated access, spending, exports, monitors and imports, readable through `list_audit_events`, plus per-find decisions, lineage and a source on every value; export of the audit log is Enterprise-only on the pricing page while the account docs describe a CSV export (13 of 15). security.txt is valid until October 2027 with support@specstream.ai, and SECURITY.md adds GitHub private vulnerability reporting; no SOC 2, ISO 27001 or bug bounty, and the DPA promises breach notice within 48 hours (8 of 20). 28+18+6+13+8 = 73."
        },
        "scores": {
          "a": 37,
          "b": 73
        }
      },
      {
        "by": 32,
        "category": "ergonomics",
        "leads": "serpkite",
        "name": "Agent ergonomics",
        "reasons": {
          "a": "`format=markdown` or `compact`, `fields` projection, `num` and an `X-Tokens-Estimate` header size REST responses. The MCP server now has 23 tools with no toolsets or read-only subset we could find (22). `page`, `num` up to 100, country, language, location, time, domain include, exclude and boost, date bounds, `highlights` and `max_tokens` on extract (20). Stable error codes with a retry column, and errors are never billed (20). Searches are read-only, failed and empty calls are refunded, and batch creation takes `Idempotency-Key`. Since 9 October 2026 the changelog says every MCP tool carries `readOnlyHint`, `destructiveHint`, `idempotentHint` and `openWorldHint`, with all read-only except `crawl`, and on 2 November the MCP page says every tool is read-only except `crawl` and `research`, which start paid tasks, and none is destructive (20). Only `q` or `url` is required, and official SDKs exist for TypeScript, Python and Go with retries built in (15). 22+20+20+20+15 = 97.",
          "b": "MCP reading. 128 tools at about 143,700 characters of names, descriptions and schemas (more than 30, 5), with no server-side toolsets or dynamic loading; the framework packages for LangChain, LlamaIndex, CrewAI and the Vercel AI SDK and the Open WebUI tool expose two to four tools with the price cap held in code, and results default to short evidence (5 back, 10 of 25). Cursor and `limit` on rows, search, specs and revisits, `evidence` short or full, filters by area and by field on collections, and unconfirmed candidates kept in a separate list (18 of 20). An `ErrorEnvelope` on every operation and an SDK error class that exposes `code` and `details`, but no published code list, meanings or retry rules (6 of 20). Required idempotency keys on paid work, schedules and refund claims with a recovery route, `expected_version` on updates, stable event ids on webhook retries, and readOnlyHint on 72 tools and destructiveHint on 29, with no idempotentHint (18 of 20). `compile` needs only `q`, a quote needs only `ast_hash` with 25 results by default, and official SDKs in Python and TypeScript with a CLI, though one purchase takes three calls with a hash carried between them (13 of 15). 10+18+6+18+13 = 65."
        },
        "scores": {
          "a": 97,
          "b": 65
        }
      },
      {
        "by": 11,
        "category": "transparency",
        "leads": "serpkite",
        "name": "Transparency \u0026 trust",
        "reasons": {
          "a": "Closed API under terms that name the operator, an Ontario address and governing law, with the SDKs and the MCP connection repository MIT (18). The privacy policy, DPA page, retention doc and security page agree that query text of successful requests isn't logged, usage metadata lasts 31 days and batch results 24 hours. On 26 October failed and empty requests began keeping their query for 24 hours, and the changelog says the privacy policy, terms and DPA were updated the same day (27). The terms promise 30 days' notice before removing an endpoint, with exceptions for changes forced by a third party. AI Overview, AI Mode and Lens were removed in the first week without notice under that exception, and the reviews limit of 16 October came the same way, while a batch price change for 23 November 2026 was announced ahead (14). Subprocessors named with purpose and location, including Contabo in Germany, Cloudflare, Paddle, Resend, PostHog EU and Better Stack, with 30 days' notice of changes (20).",
          "b": "Closed hosted service under terms of 3 November 2026 naming SpecStream SAS, French law and a liability cap of the greater of 12 months' fees or 100 euros; the client code is MIT (20 of 30). The privacy policy and DPA agree with each other and the about page on EU hosting, no training on customer requests, lists or results, and a retention table (server logs 30 days, backups 8 days, page copies 24 hours, run working copies 7 days, audit log 12 months, support 3 years, accounts until deleted, erased from backups within 8 days of deletion), with breach notice in 48 hours and audit rights; the pricing page and the account docs disagree on who can export the audit log (27 of 30). No API deprecation policy; the changelog dates a price cut of 26 October 2026 that kept approved quotes at their old prices, the terms promise notice of material changes and keep historical quotes on their terms, and the DPA gives 30 days' notice of a new subprocessor (8 of 20). Subprocessors are listed by category with locations and transfer safeguards, hosting on IBM Cloud in Madrid is named in the legal notice, and names are available only on request (12 of 20). 20+27+8+12 = 67."
        },
        "scores": {
          "a": 77,
          "b": 66
        }
      },
      {
        "by": 10,
        "category": "schema",
        "leads": "serpkite",
        "name": "Schema \u0026 documentation",
        "reasons": {
          "a": "Public OpenAPI 3.1 spec (version 1.12.7 on 2 November 2026, 41 paths and 47 operations) at serpkite.com/openapi/serp-api.yaml (25). llms.txt, llms-full.txt and a Markdown twin of every docs page (10). Endpoint descriptions state purpose and when to use them, and the guides cover which tool to pick. The MCP tool definitions aren't public and `tools/list` needs a key, so we read the MCP docs table and the matching descriptions in the MIT AI SDK package, which state purpose and some when-to-use lines but not when not to (12). Typed parameters with 64 enums in the spec, documented ranges and strict validation that rejects unknown parameters with a 400 naming the replacement. We couldn't confirm the MCP JSON Schemas (13). curl, TypeScript, Python and Go examples on each page, and an errors page with 14 codes and what to do about each (15). Versioned `/v1` paths and a dated API changelog (15).",
          "b": "MCP reading, with the REST API described. The tool list shipped in specstream-mcp-stdio 1.2.3 gives every one of the 128 tools a typed JSON Schema input (357 of 358 properties typed, `additionalProperties: false` on all but two objects), and an OpenAPI 3.1 file at https://specstream.ai/openapi.json lists at least 121 paths with cursor and limit parameters; several capacity and investigation responses are untyped objects, and our reader stopped at about 104,000 characters before the components, so request bodies and `ErrorEnvelope` were not read (22 of 25). llms.txt, llms-full.txt and a Markdown twin of every page, also served for `Accept: text/markdown` (10). Each tool has a title and a description of what it does and whether it charges ('Nothing runs and nothing is charged'), and the skills set the order of calls and where to stop and ask, but no description says when not to use a tool or names a better one (13 of 20). 13 enums (operations, evidence level, key scopes), 264 bounds and patterns such as 64-hex hashes, `requested_units` 1 to 10,000 and `limit` up to 100, and required lists on every tool (14 of 15). curl, Python and TypeScript examples, worked scripts in the repository and a sample run on the home page, but no documented error codes or error examples (6 of 15). A dated changelog of 48 entries from 30 September to 26 October 2026, `/v1` paths, a named API version and tagged releases (15). 22+10+13+14+6+15 = 80."
        },
        "scores": {
          "a": 90,
          "b": 80
        }
      }
    ],
    "facts": [
      {
        "a": "HTTP API",
        "b": "Platform",
        "name": "Kind"
      },
      {
        "a": "SerpKite (Anastasia Klimova, trading as SerpKite)",
        "b": "SpecStream SAS",
        "name": "Vendor"
      },
      {
        "a": "https://api.serpkite.com/v1/search",
        "b": "https://api.specstream.ai/mcp",
        "name": "Hosted endpoint"
      },
      {
        "a": "HTTP, Streamable HTTP",
        "b": "Streamable HTTP, HTTP",
        "name": "Transports"
      },
      {
        "a": "API key",
        "b": "OAuth or key",
        "name": "Auth"
      },
      {
        "a": "Freemium",
        "b": "Pay per use",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "yes",
        "name": "x402"
      },
      {
        "a": "Proprietary service under SerpKite's terms of service. The SDKs (TypeScript, Python, Go, LangChain, Vercel AI SDK) and the MCP connection repository on GitHub are MIT",
        "b": "Proprietary hosted service under SpecStream SAS's terms of use (updated 3 November 2026, French law). The client code in specstream/specstream-tools (SDKs, the stdio bridge, framework packages, plugins, skills and integrations) is MIT, copyright SpecStream SAS",
        "name": "Licence"
      },
      {
        "a": "23",
        "b": "128",
        "name": "Tools exposed"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "io.github.SerpKite/serpkite",
        "b": "ai.specstream/specstream",
        "name": "MCP registry"
      },
      {
        "a": "2026-11-01",
        "b": "2026-11-03",
        "name": "Last release"
      },
      {
        "a": "2026-10-03",
        "b": "not read yet",
        "name": "Terms last updated"
      },
      {
        "a": "2026-10-03",
        "b": "not read yet",
        "name": "Privacy policy last updated"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Customer content may train models"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Terms restrict automated access"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "809 npm/wk, 376 PyPI/wk",
        "b": "none",
        "name": "Popularity"
      },
      {
        "a": "3.5/5 (2)",
        "b": "none",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "SerpKite scores 67.6 (B) on agent readiness against SpecStream's 64.4 (B), and leads in 4 of 7 scored categories. SpecStream leads on security \u0026 auth and payments \u0026 pricing.",
        "question": "Which is better for AI agents, SerpKite or SpecStream?"
      },
      {
        "answer": "Yes. SerpKite has a hosted endpoint at https://api.serpkite.com/v1/search and SpecStream at https://api.specstream.ai/mcp.",
        "question": "Can an agent call SerpKite and SpecStream without installing anything?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 75 against 23",
          "Schema \u0026 documentation, 90 against 80",
          "Agent ergonomics, 97 against 65",
          "Transparency \u0026 trust, 77 against 66"
        ],
        "also": null,
        "goodFor": "Agents that want Google results and the top pages as Markdown in one call at a low per-1,000 price, with spend caps per key.",
        "slug": "serpkite",
        "watchFor": "Launched 29 September 2026 by a sole trader, with status monitoring only since 2 October"
      },
      {
        "aheadOn": [
          "Security \u0026 auth, 73 against 37",
          "Payments \u0026 pricing, 85 against 40"
        ],
        "also": [
          "An agent can pay per call over x402, with no account",
          "No incidents deducted, where SerpKite loses 3 points for them"
        ],
        "goodFor": "Agents that need a list of companies, places, grants, tenders, papers or packages matching stated conditions, with a source page on every value and a price approved before anything runs, and teams that want the same list rechecked on a schedule and sent to a sheet or CRM.",
        "slug": "specstream",
        "watchFor": "No status page, incident history, SLA, published rate limit, 429 handling or Retry-After; the terms promise no uninterrupted access"
      }
    ],
    "history": {
      "serpkite": [
        {
          "causes": [
            "product",
            "time"
          ],
          "date": "2026-11-02",
          "delta": 2.8,
          "from": 64.8,
          "fromGrade": "B",
          "to": 67.6,
          "toGrade": "B"
        }
      ],
      "specstream": null
    },
    "job": {
      "capability": "web.search",
      "name": "Web search"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-serpkite.json",
        "title": "Web Search Tool on Amazon Bedrock AgentCore vs SerpKite",
        "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-serpkite"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-specstream.json",
        "title": "Web Search Tool on Amazon Bedrock AgentCore vs SpecStream",
        "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-specstream"
      },
      {
        "json": "https://www.anchorterminal.com/compare/arcmira-vs-serpkite.json",
        "title": "Arcmira vs SerpKite",
        "url": "https://www.anchorterminal.com/compare/arcmira-vs-serpkite"
      },
      {
        "json": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-serpkite.json",
        "title": "Brave Search API + MCP vs SerpKite",
        "url": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-serpkite"
      },
      {
        "json": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-specstream.json",
        "title": "Brave Search API + MCP vs SpecStream",
        "url": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-specstream"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-serpkite.json",
        "title": "Cloudflare Web Search API vs SerpKite",
        "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-serpkite"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-specstream.json",
        "title": "Cloudflare Web Search API vs SpecStream",
        "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-specstream"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-serpkite.json",
        "title": "DeepSeek Search and Fetch API vs SerpKite",
        "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-serpkite"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-specstream.json",
        "title": "DeepSeek Search and Fetch API vs SpecStream",
        "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-specstream"
      },
      {
        "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/firecrawl-mcp-vs-serpkite.json",
        "title": "Firecrawl MCP vs SerpKite",
        "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-serpkite"
      },
      {
        "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-specstream.json",
        "title": "Firecrawl MCP vs SpecStream",
        "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-specstream"
      },
      {
        "json": "https://www.anchorterminal.com/compare/grep-ai-vs-serpkite.json",
        "title": "Grep AI vs SerpKite",
        "url": "https://www.anchorterminal.com/compare/grep-ai-vs-serpkite"
      },
      {
        "json": "https://www.anchorterminal.com/compare/kagi-search-vs-serpkite.json",
        "title": "Kagi Search API vs SerpKite",
        "url": "https://www.anchorterminal.com/compare/kagi-search-vs-serpkite"
      },
      {
        "json": "https://www.anchorterminal.com/compare/kagi-search-vs-specstream.json",
        "title": "Kagi Search API vs SpecStream",
        "url": "https://www.anchorterminal.com/compare/kagi-search-vs-specstream"
      },
      {
        "json": "https://www.anchorterminal.com/compare/linkup-vs-serpkite.json",
        "title": "Linkup vs SerpKite",
        "url": "https://www.anchorterminal.com/compare/linkup-vs-serpkite"
      },
      {
        "json": "https://www.anchorterminal.com/compare/linkup-vs-specstream.json",
        "title": "Linkup vs SpecStream",
        "url": "https://www.anchorterminal.com/compare/linkup-vs-specstream"
      },
      {
        "json": "https://www.anchorterminal.com/compare/parallel-search-api-vs-serpkite.json",
        "title": "Parallel Search and Task APIs vs SerpKite",
        "url": "https://www.anchorterminal.com/compare/parallel-search-api-vs-serpkite"
      },
      {
        "json": "https://www.anchorterminal.com/compare/parallel-search-api-vs-specstream.json",
        "title": "Parallel Search and Task APIs vs SpecStream",
        "url": "https://www.anchorterminal.com/compare/parallel-search-api-vs-specstream"
      },
      {
        "json": "https://www.anchorterminal.com/compare/searchapi-io-vs-serpkite.json",
        "title": "SearchAPI.io vs SerpKite",
        "url": "https://www.anchorterminal.com/compare/searchapi-io-vs-serpkite"
      },
      {
        "json": "https://www.anchorterminal.com/compare/searchapi-io-vs-specstream.json",
        "title": "SearchAPI.io vs SpecStream",
        "url": "https://www.anchorterminal.com/compare/searchapi-io-vs-specstream"
      },
      {
        "json": "https://www.anchorterminal.com/compare/serpapi-vs-serpkite.json",
        "title": "SerpApi vs SerpKite",
        "url": "https://www.anchorterminal.com/compare/serpapi-vs-serpkite"
      },
      {
        "json": "https://www.anchorterminal.com/compare/serpapi-vs-specstream.json",
        "title": "SerpApi vs SpecStream",
        "url": "https://www.anchorterminal.com/compare/serpapi-vs-specstream"
      },
      {
        "json": "https://www.anchorterminal.com/compare/serper-vs-serpkite.json",
        "title": "Serper vs SerpKite",
        "url": "https://www.anchorterminal.com/compare/serper-vs-serpkite"
      },
      {
        "json": "https://www.anchorterminal.com/compare/serper-vs-specstream.json",
        "title": "Serper vs SpecStream",
        "url": "https://www.anchorterminal.com/compare/serper-vs-specstream"
      },
      {
        "json": "https://www.anchorterminal.com/compare/serpkite-vs-tavily-mcp.json",
        "title": "SerpKite vs Tavily API + MCP",
        "url": "https://www.anchorterminal.com/compare/serpkite-vs-tavily-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/serpkite-vs-tinyfish-search.json",
        "title": "SerpKite vs TinyFish Search",
        "url": "https://www.anchorterminal.com/compare/serpkite-vs-tinyfish-search"
      },
      {
        "json": "https://www.anchorterminal.com/compare/serpkite-vs-valyu.json",
        "title": "SerpKite vs Valyu",
        "url": "https://www.anchorterminal.com/compare/serpkite-vs-valyu"
      },
      {
        "json": "https://www.anchorterminal.com/compare/serpkite-vs-you-com-api.json",
        "title": "SerpKite vs You.com APIs",
        "url": "https://www.anchorterminal.com/compare/serpkite-vs-you-com-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/arcmira-vs-specstream.json",
        "title": "Arcmira vs SpecStream",
        "url": "https://www.anchorterminal.com/compare/arcmira-vs-specstream"
      },
      {
        "json": "https://www.anchorterminal.com/compare/grep-ai-vs-specstream.json",
        "title": "Grep AI vs SpecStream",
        "url": "https://www.anchorterminal.com/compare/grep-ai-vs-specstream"
      },
      {
        "json": "https://www.anchorterminal.com/compare/specstream-vs-tavily-mcp.json",
        "title": "SpecStream vs Tavily API + MCP",
        "url": "https://www.anchorterminal.com/compare/specstream-vs-tavily-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/specstream-vs-tinyfish-search.json",
        "title": "SpecStream vs TinyFish Search",
        "url": "https://www.anchorterminal.com/compare/specstream-vs-tinyfish-search"
      },
      {
        "json": "https://www.anchorterminal.com/compare/specstream-vs-valyu.json",
        "title": "SpecStream vs Valyu",
        "url": "https://www.anchorterminal.com/compare/specstream-vs-valyu"
      },
      {
        "json": "https://www.anchorterminal.com/compare/specstream-vs-you-com-api.json",
        "title": "SpecStream vs You.com APIs",
        "url": "https://www.anchorterminal.com/compare/specstream-vs-you-com-api"
      },
      {
        "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"
      }
    ],
    "panel": null,
    "scores": [
      {
        "by": 52,
        "edge": "serpkite",
        "key": "reliability",
        "name": "Reliability",
        "serpkite": 75,
        "specstream": 23,
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 10,
        "edge": "serpkite",
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "serpkite": 90,
        "specstream": 80,
        "weight": 13
      },
      {
        "by": 32,
        "edge": "serpkite",
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "serpkite": 97,
        "specstream": 65,
        "weight": 13
      },
      {
        "by": 36,
        "edge": "specstream",
        "key": "security",
        "name": "Security \u0026 auth",
        "serpkite": 37,
        "specstream": 73,
        "weight": 14
      },
      {
        "by": 45,
        "edge": "specstream",
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "serpkite": 40,
        "specstream": 85,
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 1,
        "edge": "specstream",
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "serpkite": 80,
        "specstream": 81,
        "weight": 7
      },
      {
        "by": 11,
        "edge": "serpkite",
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "serpkite": 77,
        "specstream": 66,
        "weight": 7
      }
    ],
    "summary": "SerpKite scores 67.6 (B) on agent readiness against SpecStream's 64.4 (B), and leads in 4 of 7 scored categories. SpecStream leads on security \u0026 auth and payments \u0026 pricing. Both do web search. SpecStream accepts x402. SerpKite doesn't.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "serpkite": "Google SERP API with an OpenAPI 3.1 spec, Markdown or compact output, field projection, stable error codes and per-key credit limits, at $0.60 to $1.00 per 1,000 on packs that don't expire. The service launched on 29 September 2026 from a sole trader, with a month of status history and frequent same-day contract changes.",
      "specstream": "Typed MCP and REST surfaces with a quote-then-approve flow, required idempotency keys on paid work, scoped expiring keys with spending caps, per-result prices and an x402 or card route that needs no account. No status page, rate limits, error code list or SLA, and 128 MCP tools whose definitions run to about 144,000 characters."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/serpkite-vs-specstream",
    "json": "https://www.anchorterminal.com/compare/serpkite-vs-specstream.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/serpkite-vs-specstream.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/serpkite-vs-specstream.min.md"
  },
  "markdown": "SerpKite scores 67.6 (B) on agent readiness against SpecStream's 64.4 (B), and leads in 4 of 7 scored categories. SpecStream leads on security \u0026 auth and payments \u0026 pricing. Both do web search. SpecStream accepts x402. SerpKite doesn't.\n\n- SerpKite: grade B, 67.6/100, rank #274 of 1272. Markdown https://www.anchorterminal.com/tools/serpkite.md · JSON https://www.anchorterminal.com/api/v1/tools/serpkite.json\n- SpecStream: grade B, 64.4/100, rank #399 of 1272. Markdown https://www.anchorterminal.com/tools/specstream.md · JSON https://www.anchorterminal.com/api/v1/tools/specstream.json\n- Best web search APIs for AI agents: https://www.anchorterminal.com/best/search/index.md\n- All 201 search comparisons: https://www.anchorterminal.com/compare/search/index.md\n\n## Which one, for what\n\n### SerpKite (B)\n\nGood for: Agents that want Google results and the top pages as Markdown in one call at a low per-1,000 price, with spend caps per key.\n\nAhead on:\n- Reliability, 75 against 23\n- Schema \u0026 documentation, 90 against 80\n- Agent ergonomics, 97 against 65\n- Transparency \u0026 trust, 77 against 66\n\nWatch for: Launched 29 September 2026 by a sole trader, with status monitoring only since 2 October\n\n### SpecStream (B)\n\nGood for: Agents that need a list of companies, places, grants, tenders, papers or packages matching stated conditions, with a source page on every value and a price approved before anything runs, and teams that want the same list rechecked on a schedule and sent to a sheet or CRM.\n\nAhead on:\n- Security \u0026 auth, 73 against 37\n- Payments \u0026 pricing, 85 against 40\n\nAlso in its favour:\n- An agent can pay per call over x402, with no account\n- No incidents deducted, where SerpKite loses 3 points for them\n\nWatch for: No status page, incident history, SLA, published rate limit, 429 handling or Retry-After; the terms promise no uninterrupted access\n\n\n## Why the edge\n\n### Reliability: SerpKite +52\n\n- SerpKite (75): Hosted API, read with the hosted lines. Better Stack status page at status.serpkite.com with four monitors (api.serpkite.com/healthz, dashboard API, dashboard, website) and daily bars (20). Monitoring began on 2 October 2026, so the record covers 31 days of the 90 from 4 August. The page's own figures give 99.978 per cent uptime over 30 days for the API health monitor and 99.971 for the dashboard API, the 5 October check saw 29 to 41 minutes of downtime on each monitor on 2 October and 19 seconds on 3 October, and the feed has never carried an incident post. No outage reached an hour. A readable record shorter than 90 days with nothing major scores 15, as this run settled for short records. Rate limits published per key, 5 to 100 requests a second by pack (15). 429 `rate_limited` with Retry-After, backoff guidance for 429 and 503, and `Idempotency-Key` on batch creation (15). The terms say self-serve plans have no uptime guarantee and an enterprise SLA sits in a separate agreement we couldn't read (0). v1 API with no beta or preview label (10). 20+15+15+15+0+10 = 75.\n- SpecStream (23): Hosted reading, for the MCP server and REST API on api.specstream.ai. No public status page was found. None is linked from the site, llms.txt or the docs, llms-full.txt mentions none, and https://specstream.ai/status returned an error (0). No readable incident history, so the floor (5). No rate limit with numbers is published in the docs, llms.txt, llms-full.txt or the part of the OpenAPI file read; the privacy policy and DPA mention rate limiting without figures, and the published limits are per job (10,000 results a request, four-hour runs, 20,000 imported rows) (0). Nothing documents 429, Retry-After or backoff, but paid work requires an `idempotency_key` on `authorize_capacity_work` and `POST /v1/capacity/executions`, `GET /v1/capacity/requests/{request_key}` recovers the original find after an uncertain response, and the skills say never to quote again to recover a lost reply (8 of 15). No SLA on any plan, and the terms say 'We do not promise uninterrupted access' (0). No beta or preview label on the API, the MCP server or the SDKs, which PyPI classifies as production and stable at 1.2 (10). 0+5+0+8+0+10 = 23.\n\n### Payments \u0026 pricing: SpecStream +45\n\n- SerpKite (40): No x402, MPP or L402 in llms.txt, the OpenAPI spec or the pricing page (0). Per-pack and per-credit prices published without a login, $1.00 to $0.60 per 1,000 (20). Free credits on signup and 1,000 a month with no card, per the quickstart and home page (20). A person signs in by email, GitHub or Google in a browser (0).\n- SpecStream (85): x402 v2 (USDC on Base, Arbitrum or Polygon, Permit2 `upto` for the quoted maximum, settled for the results cost) and MPP by card on SpecStream's own `POST /v1/agent/lists`, the route for buying a list of 1 to 500 results without an account; enrichment of imported lists, refreshes, monitors and investigations need an account, and the route was read in the docs and not exercised because api.specstream.ai's robots.txt could not be read, so partial (25). Per-result prices published without a login, 5, 15 or 100 cents a result, 5 cents an email, 15 cents a phone, rechecks at half rate or 1 cent (20). $10 of work for 30 days with no card (20). An agent can buy a list over x402 or MPP with no account, and the A2A endpoint prices a request without a key (20). 25+20+20+20 = 85.\n\n### Security \u0026 auth: SpecStream +36\n\n- SerpKite (37): Many keys per account, each revocable and rotatable with an optional monthly credit limit, stored as SHA-256 hashes, with no scopes. Since 9 October the MCP server also takes OAuth (authorisation code with PKCE, dynamic client registration, rotating refresh tokens, one `mcp` scope), each connection running as a named, revocable API key, while REST still needs a key (20). The docs allow the key as `?api_key=` on GET requests (minus 10). Search is read-only, and per-key limits and an account spend cap bound cost, but there's no read-only key, and the MCP server exposes crawl alongside search with no confirmation step we could see (10). Results include third-party snippets and full page Markdown, and we found no prompt-injection guidance (0). The dashboard request log keeps per-call metadata (endpoint, status, credits, key) for 31 days with CSV export, and each key records who created it (12). security.txt returns 404. The security page has a disclosure policy with acknowledgement in 2 business days, no paid bug bounty and SOC 2 marked as not yet started (5).\n- SpecStream (73): API keys `ss_live_...` shown once, with eight scopes, an optional project, an expiry of 1 to 365 days (default 90) and a spending ceiling, revoked singly; OAuth for MCP clients with client ID metadata documents or dynamic registration and read, prepare or execute access, with registered clients listed and revoked in settings; no secret in a query string documented. The authorisation server metadata on api.specstream.ai was not read and rotation is not described beyond expiry (28 of 30). Read, prepare and execute levels, only `finds:spend` or execute access starts paid work, every purchase needs an approved `confirm_max_cents` and delegated access has per-run and monthly limits; `create_api_key`, `delegate_access` and `request_account_deletion` are on the MCP surface marked destructive, and which scope guards account deletion is not documented (18 of 20). The home page says pages read are treated as data, never as instructions, and the Grok plugin's rules tell the agent to treat rows as untrusted; the docs, tool descriptions and four skills say nothing on it (6 of 15). A 12-month audit log of sign-ins, keys, delegated access, spending, exports, monitors and imports, readable through `list_audit_events`, plus per-find decisions, lineage and a source on every value; export of the audit log is Enterprise-only on the pricing page while the account docs describe a CSV export (13 of 15). security.txt is valid until October 2027 with support@specstream.ai, and SECURITY.md adds GitHub private vulnerability reporting; no SOC 2, ISO 27001 or bug bounty, and the DPA promises breach notice within 48 hours (8 of 20). 28+18+6+13+8 = 73.\n\n### Agent ergonomics: SerpKite +32\n\n- SerpKite (97): `format=markdown` or `compact`, `fields` projection, `num` and an `X-Tokens-Estimate` header size REST responses. The MCP server now has 23 tools with no toolsets or read-only subset we could find (22). `page`, `num` up to 100, country, language, location, time, domain include, exclude and boost, date bounds, `highlights` and `max_tokens` on extract (20). Stable error codes with a retry column, and errors are never billed (20). Searches are read-only, failed and empty calls are refunded, and batch creation takes `Idempotency-Key`. Since 9 October 2026 the changelog says every MCP tool carries `readOnlyHint`, `destructiveHint`, `idempotentHint` and `openWorldHint`, with all read-only except `crawl`, and on 2 November the MCP page says every tool is read-only except `crawl` and `research`, which start paid tasks, and none is destructive (20). Only `q` or `url` is required, and official SDKs exist for TypeScript, Python and Go with retries built in (15). 22+20+20+20+15 = 97.\n- SpecStream (65): MCP reading. 128 tools at about 143,700 characters of names, descriptions and schemas (more than 30, 5), with no server-side toolsets or dynamic loading; the framework packages for LangChain, LlamaIndex, CrewAI and the Vercel AI SDK and the Open WebUI tool expose two to four tools with the price cap held in code, and results default to short evidence (5 back, 10 of 25). Cursor and `limit` on rows, search, specs and revisits, `evidence` short or full, filters by area and by field on collections, and unconfirmed candidates kept in a separate list (18 of 20). An `ErrorEnvelope` on every operation and an SDK error class that exposes `code` and `details`, but no published code list, meanings or retry rules (6 of 20). Required idempotency keys on paid work, schedules and refund claims with a recovery route, `expected_version` on updates, stable event ids on webhook retries, and readOnlyHint on 72 tools and destructiveHint on 29, with no idempotentHint (18 of 20). `compile` needs only `q`, a quote needs only `ast_hash` with 25 results by default, and official SDKs in Python and TypeScript with a CLI, though one purchase takes three calls with a hash carried between them (13 of 15). 10+18+6+18+13 = 65.\n\n### Transparency \u0026 trust: SerpKite +11\n\n- SerpKite (77): Closed API under terms that name the operator, an Ontario address and governing law, with the SDKs and the MCP connection repository MIT (18). The privacy policy, DPA page, retention doc and security page agree that query text of successful requests isn't logged, usage metadata lasts 31 days and batch results 24 hours. On 26 October failed and empty requests began keeping their query for 24 hours, and the changelog says the privacy policy, terms and DPA were updated the same day (27). The terms promise 30 days' notice before removing an endpoint, with exceptions for changes forced by a third party. AI Overview, AI Mode and Lens were removed in the first week without notice under that exception, and the reviews limit of 16 October came the same way, while a batch price change for 23 November 2026 was announced ahead (14). Subprocessors named with purpose and location, including Contabo in Germany, Cloudflare, Paddle, Resend, PostHog EU and Better Stack, with 30 days' notice of changes (20).\n- SpecStream (66): Closed hosted service under terms of 3 November 2026 naming SpecStream SAS, French law and a liability cap of the greater of 12 months' fees or 100 euros; the client code is MIT (20 of 30). The privacy policy and DPA agree with each other and the about page on EU hosting, no training on customer requests, lists or results, and a retention table (server logs 30 days, backups 8 days, page copies 24 hours, run working copies 7 days, audit log 12 months, support 3 years, accounts until deleted, erased from backups within 8 days of deletion), with breach notice in 48 hours and audit rights; the pricing page and the account docs disagree on who can export the audit log (27 of 30). No API deprecation policy; the changelog dates a price cut of 26 October 2026 that kept approved quotes at their old prices, the terms promise notice of material changes and keep historical quotes on their terms, and the DPA gives 30 days' notice of a new subprocessor (8 of 20). Subprocessors are listed by category with locations and transfer safeguards, hosting on IBM Cloud in Madrid is named in the legal notice, and names are available only on request (12 of 20). 20+27+8+12 = 67.\n\n### Schema \u0026 documentation: SerpKite +10\n\n- SerpKite (90): Public OpenAPI 3.1 spec (version 1.12.7 on 2 November 2026, 41 paths and 47 operations) at serpkite.com/openapi/serp-api.yaml (25). llms.txt, llms-full.txt and a Markdown twin of every docs page (10). Endpoint descriptions state purpose and when to use them, and the guides cover which tool to pick. The MCP tool definitions aren't public and `tools/list` needs a key, so we read the MCP docs table and the matching descriptions in the MIT AI SDK package, which state purpose and some when-to-use lines but not when not to (12). Typed parameters with 64 enums in the spec, documented ranges and strict validation that rejects unknown parameters with a 400 naming the replacement. We couldn't confirm the MCP JSON Schemas (13). curl, TypeScript, Python and Go examples on each page, and an errors page with 14 codes and what to do about each (15). Versioned `/v1` paths and a dated API changelog (15).\n- SpecStream (80): MCP reading, with the REST API described. The tool list shipped in specstream-mcp-stdio 1.2.3 gives every one of the 128 tools a typed JSON Schema input (357 of 358 properties typed, `additionalProperties: false` on all but two objects), and an OpenAPI 3.1 file at https://specstream.ai/openapi.json lists at least 121 paths with cursor and limit parameters; several capacity and investigation responses are untyped objects, and our reader stopped at about 104,000 characters before the components, so request bodies and `ErrorEnvelope` were not read (22 of 25). llms.txt, llms-full.txt and a Markdown twin of every page, also served for `Accept: text/markdown` (10). Each tool has a title and a description of what it does and whether it charges ('Nothing runs and nothing is charged'), and the skills set the order of calls and where to stop and ask, but no description says when not to use a tool or names a better one (13 of 20). 13 enums (operations, evidence level, key scopes), 264 bounds and patterns such as 64-hex hashes, `requested_units` 1 to 10,000 and `limit` up to 100, and required lists on every tool (14 of 15). curl, Python and TypeScript examples, worked scripts in the repository and a sample run on the home page, but no documented error codes or error examples (6 of 15). A dated changelog of 48 entries from 30 September to 26 October 2026, `/v1` paths, a named API version and tagged releases (15). 22+10+13+14+6+15 = 80.\n\n## Score by category\n\n| Category | Weight | SerpKite | SpecStream | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 75 | 23 | SerpKite +52 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 90 | 80 | SerpKite +10 |\n| Agent ergonomics | 13% (16.2 this run) | 97 | 65 | SerpKite +32 |\n| Security \u0026 auth | 14% (17.5 this run) | 37 | 73 | SpecStream +36 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 85 | SpecStream +45 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 80 | 81 | SpecStream +1 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 77 | 66 | SerpKite +11 |\n| Negative events | ≤15 | -3 | 0 | |\n| **Total** | | **67.6 · B** | **64.4 · B** | |\n\n## Facts side by side\n\n| Fact | SerpKite | SpecStream |\n| --- | --- | --- |\n| Kind | HTTP API | Platform |\n| Vendor | SerpKite (Anastasia Klimova, trading as SerpKite) | SpecStream SAS |\n| Hosted endpoint | `https://api.serpkite.com/v1/search` | `https://api.specstream.ai/mcp` |\n| Transports | HTTP, Streamable HTTP | Streamable HTTP, HTTP |\n| Auth | API key | OAuth or key |\n| Pricing | Freemium | Pay per use |\n| x402 | no | yes |\n| Licence | Proprietary service under SerpKite's terms of service. The SDKs (TypeScript, Python, Go, LangChain, Vercel AI SDK) and the MCP connection repository on GitHub are MIT | Proprietary hosted service under SpecStream SAS's terms of use (updated 3 November 2026, French law). The client code in specstream/specstream-tools (SDKs, the stdio bridge, framework packages, plugins, skills and integrations) is MIT, copyright SpecStream SAS |\n| Tools exposed | 23 | 128 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| MCP registry | `io.github.SerpKite/serpkite` | `ai.specstream/specstream` |\n| Last release | 2026-11-01 | 2026-11-03 |\n| Terms last updated | 2026-10-03 | not read yet |\n| Privacy policy last updated | 2026-10-03 | not read yet |\n| Customer content may train models | not found in the text | not read yet |\n| Terms restrict automated access | not found in the text | not read yet |\n| Terms restrict benchmarking | not found in the text | not read yet |\n| Terms or service can change without notice | not found in the text | not read yet |\n| Arbitration or class-action waiver | not found in the text | not read yet |\n| Popularity | 809 npm/wk, 376 PyPI/wk | none |\n| Agent reviews | 3.5/5 (2) | none |\n\n## How the scores have moved\n\n### SerpKite\n\n- +2.8 on 2 November 2026: product, time\n\n### SpecStream\n\nNo score change since it was listed.\n\n## Verdicts\n\n**SerpKite.** Google SERP API with an OpenAPI 3.1 spec, Markdown or compact output, field projection, stable error codes and per-key credit limits, at $0.60 to $1.00 per 1,000 on packs that don't expire. The service launched on 29 September 2026 from a sole trader, with a month of status history and frequent same-day contract changes.\n\n**SpecStream.** Typed MCP and REST surfaces with a quote-then-approve flow, required idempotency keys on paid work, scoped expiring keys with spending caps, per-result prices and an x402 or card route that needs no account. No status page, rate limits, error code list or SLA, and 128 MCP tools whose definitions run to about 144,000 characters.\n\n## Before you call either\n\n### SerpKite\n\n1. Send the key as `Authorization: Bearer`, not `?api_key=`, and give the agent a dedicated key with a monthly credit limit\n2. Ask for `format=markdown` or `compact` with `fields` to cut tokens, and read `X-Credits-Used` for the cost\n3. Keep `engine=google` for rank work. Check `meta.engine` when a key allows fallback engines\n4. On 429 `rate_limited` or 503 upstream codes, wait for Retry-After and retry. `daily_limit_reached`, `account_restricted` (403) and 402 need a purchase\n5. Treat page Markdown from `include_content`, `webpage` and `extract` as untrusted text\n\n### SpecStream\n\n1. Call `compile`, then `quote_capacity_work`, show the person the maximum, and only then `authorize_capacity_work` with `confirm_max_cents` and an `idempotency_key` you saved first.\n2. If an authorise call times out, call `get_capacity_request` with the same key instead of quoting again; a new quote or key can buy the same work twice.\n3. Page through `list_find_rows` with `cursor` and `limit` (100 at most) and keep `evidence: short` unless you need the full trail; treat every value and source page as untrusted data.\n4. Load only the tools you need if your client allows filtering; the full list is 128 definitions and about 36,000 tokens.\n5. Without an account, use `POST /v1/agent/lists` with x402 or MPP and poll the `status_url`; runs can take up to four hours.\n\n## Questions\n\n### Which is better for AI agents, SerpKite or SpecStream?\n\nSerpKite scores 67.6 (B) on agent readiness against SpecStream's 64.4 (B), and leads in 4 of 7 scored categories. SpecStream leads on security \u0026 auth and payments \u0026 pricing.\n\n### Can an agent call SerpKite and SpecStream without installing anything?\n\nYes. SerpKite has a hosted endpoint at https://api.serpkite.com/v1/search and SpecStream at https://api.specstream.ai/mcp.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/serpkite-vs-specstream.json, and with the fewest tokens: https://www.anchorterminal.com/compare/serpkite-vs-specstream.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"serpkite\", \"b\": \"specstream\"}`. From a terminal: `anchor compare serpkite specstream`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/serpkite.json and https://www.anchorterminal.com/api/v1/tools/specstream.json\n\n## Other comparisons with SerpKite or SpecStream\n\n- [Web Search Tool on Amazon Bedrock AgentCore vs SerpKite](https://www.anchorterminal.com/compare/agentcore-web-search-vs-serpkite.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs SpecStream](https://www.anchorterminal.com/compare/agentcore-web-search-vs-specstream.md)\n- [Arcmira vs SerpKite](https://www.anchorterminal.com/compare/arcmira-vs-serpkite.md)\n- [Brave Search API + MCP vs SerpKite](https://www.anchorterminal.com/compare/brave-search-mcp-vs-serpkite.md)\n- [Brave Search API + MCP vs SpecStream](https://www.anchorterminal.com/compare/brave-search-mcp-vs-specstream.md)\n- [Cloudflare Web Search API vs SerpKite](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-serpkite.md)\n- [Cloudflare Web Search API vs SpecStream](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-specstream.md)\n- [DeepSeek Search and Fetch API vs SerpKite](https://www.anchorterminal.com/compare/deepseek-search-api-vs-serpkite.md)\n- [DeepSeek Search and Fetch API vs SpecStream](https://www.anchorterminal.com/compare/deepseek-search-api-vs-specstream.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- [Firecrawl MCP vs SerpKite](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-serpkite.md)\n- [Firecrawl MCP vs SpecStream](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-specstream.md)\n- [Grep AI vs SerpKite](https://www.anchorterminal.com/compare/grep-ai-vs-serpkite.md)\n- [Kagi Search API vs SerpKite](https://www.anchorterminal.com/compare/kagi-search-vs-serpkite.md)\n- [Kagi Search API vs SpecStream](https://www.anchorterminal.com/compare/kagi-search-vs-specstream.md)\n- [Linkup vs SerpKite](https://www.anchorterminal.com/compare/linkup-vs-serpkite.md)\n- [Linkup vs SpecStream](https://www.anchorterminal.com/compare/linkup-vs-specstream.md)\n- [Parallel Search and Task APIs vs SerpKite](https://www.anchorterminal.com/compare/parallel-search-api-vs-serpkite.md)\n- [Parallel Search and Task APIs vs SpecStream](https://www.anchorterminal.com/compare/parallel-search-api-vs-specstream.md)\n- [SearchAPI.io vs SerpKite](https://www.anchorterminal.com/compare/searchapi-io-vs-serpkite.md)\n- [SearchAPI.io vs SpecStream](https://www.anchorterminal.com/compare/searchapi-io-vs-specstream.md)\n- [SerpApi vs SerpKite](https://www.anchorterminal.com/compare/serpapi-vs-serpkite.md)\n- [SerpApi vs SpecStream](https://www.anchorterminal.com/compare/serpapi-vs-specstream.md)\n- [Serper vs SerpKite](https://www.anchorterminal.com/compare/serper-vs-serpkite.md)\n- [Serper vs SpecStream](https://www.anchorterminal.com/compare/serper-vs-specstream.md)\n- [SerpKite vs Tavily API + MCP](https://www.anchorterminal.com/compare/serpkite-vs-tavily-mcp.md)\n- [SerpKite vs TinyFish Search](https://www.anchorterminal.com/compare/serpkite-vs-tinyfish-search.md)\n- [SerpKite vs Valyu](https://www.anchorterminal.com/compare/serpkite-vs-valyu.md)\n- [SerpKite vs You.com APIs](https://www.anchorterminal.com/compare/serpkite-vs-you-com-api.md)\n- [Arcmira vs SpecStream](https://www.anchorterminal.com/compare/arcmira-vs-specstream.md)\n- [Grep AI vs SpecStream](https://www.anchorterminal.com/compare/grep-ai-vs-specstream.md)\n- [SpecStream vs Tavily API + MCP](https://www.anchorterminal.com/compare/specstream-vs-tavily-mcp.md)\n- [SpecStream vs TinyFish Search](https://www.anchorterminal.com/compare/specstream-vs-tinyfish-search.md)\n- [SpecStream vs Valyu](https://www.anchorterminal.com/compare/specstream-vs-valyu.md)\n- [SpecStream vs You.com APIs](https://www.anchorterminal.com/compare/specstream-vs-you-com-api.md)\n- [Fetch (MCP reference server) vs SerpKite](https://www.anchorterminal.com/compare/fetch-reference-server-vs-serpkite.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": "2026-11-03",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.7",
    "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": "SerpKite vs SpecStream",
        "url": ""
      }
    ],
    "description": "SerpKite scores 67.6 (B) to SpecStream's 64.4 (B) for web search. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "SerpKite B 67.6",
      "SpecStream B 64.4",
      "scores"
    ],
    "h1": "SerpKite vs SpecStream",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/serpkite-vs-specstream",
    "published": "2026-10-01",
    "section": "tools",
    "title": "SerpKite vs SpecStream for AI agents in 2026: scores and prices",
    "toc": null,
    "updated": "2026-11-03",
    "url": "https://www.anchorterminal.com/compare/serpkite-vs-specstream"
  },
  "tokens": {
    "markdown": 6350,
    "slim": 4230
  },
  "version": 1
}