{
  "listings": [
    {
      "slug": "agentcore-web-search",
      "name": "Web Search Tool on Amazon Bedrock AgentCore",
      "company": "Amazon Web Services, Inc. (regional AWS entities by account location)",
      "grade": "BB",
      "fit": "yes",
      "why": "Raw results with URL and title, no model-written answer, default quota 10 Web Search requests a second per account and Region, adjustable, with queries kept inside AWS.",
      "source": "https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/gateway-target-connector-web-search-tool.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/agentcore-web-search"
    },
    {
      "slug": "exa-mcp",
      "name": "Exa API + MCP",
      "company": "Exa Labs Inc.",
      "grade": "B",
      "fit": "yes",
      "why": "Raw results at 10 QPS for /search and 100 QPS for /contents on the free tier, 402 on exhausted credit, no model-written answer in the search path.",
      "source": "https://exa.ai/docs/admin/billing.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/exa-mcp"
    },
    {
      "slug": "linkup",
      "name": "Linkup",
      "company": "Linkup Technologies SAS",
      "grade": "B",
      "fit": "yes",
      "why": "Search and fetch return raw sources at 10 queries a second per organisation, with zero data retention on request.",
      "source": "https://docs.linkup.so/pages/documentation/platform/rate-limits.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/linkup"
    },
    {
      "slug": "parallel-search-api",
      "name": "Parallel Search and Task APIs",
      "company": "Parallel Web Systems Inc.",
      "grade": "BB",
      "fit": "yes",
      "why": "Search and Extract each allow 600 requests a minute and return raw excerpts or page markdown with URLs.",
      "source": "https://docs.parallel.ai/getting-started/rate-limits.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/parallel-search-api"
    },
    {
      "slug": "brave-search-mcp",
      "name": "Brave Search API + MCP",
      "company": "Brave Software, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "Raw results, but the per-second limit is set by plan and a 429 carries X-RateLimit-Reset rather than Retry-After; 500-user deployments report constant 429s.",
      "source": "https://api-dashboard.search.brave.com/documentation/guides/rate-limiting/index.html.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/brave-search-mcp"
    },
    {
      "slug": "deepseek-search-api",
      "name": "DeepSeek Search and Fetch API",
      "company": "Hangzhou DeepSeek Artificial Intelligence Co., Ltd.",
      "grade": "C",
      "fit": "caveat",
      "why": "Raw results and pages, but 5 requests a second per account across keys is the map's blocker, and a citation-checking user will not use it for lack of zero data retention.",
      "source": "https://news.ycombinator.com/item?id=50140564",
      "confidence": "low",
      "url": "https://www.anchorterminal.com/tools/deepseek-search-api"
    },
    {
      "slug": "fetch-reference-server",
      "name": "Fetch (MCP reference server)",
      "company": "Model Context Protocol, a Series of LF Projects, LLC",
      "grade": "B",
      "fit": "caveat",
      "why": "Returns the raw page with no provider rate limit, but a robots.txt disallow, a 401, 403 or 5xx on robots.txt, and JavaScript-only pages all stop a check.",
      "source": "https://raw.githubusercontent.com/modelcontextprotocol/servers/main/src/fetch/README.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/fetch-reference-server"
    },
    {
      "slug": "liner-mcp",
      "name": "Liner Search MCP",
      "company": "Liner",
      "grade": "E",
      "fit": "caveat",
      "why": "Raw web results with no per-second limit (fair use), but no fetch, and scholar and agent calls are capped at 2 a second.",
      "source": "https://liner.com/llms-full.txt",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/liner-mcp"
    },
    {
      "slug": "mojeek",
      "name": "Mojeek Web Search API",
      "company": "Mojeek Limited",
      "grade": "F",
      "fit": "caveat",
      "why": "Raw results at 5 queries a second on Startup and 10 on Business, but no fetch and an over-limit error comes as text in a 200.",
      "source": "https://www.mojeek.com/services/search/web-search-api/",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/mojeek"
    },
    {
      "slug": "newscatcher",
      "name": "NewsCatcher",
      "company": "NewsCatcher, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "Can confirm a news article exists, but requests a second are set per plan and read from GET /subscription rather than published.",
      "source": "https://www.newscatcherapi.com/docs/get-started/rate-limits",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/newscatcher"
    },
    {
      "slug": "perplexity-search-api",
      "name": "Perplexity Search API",
      "company": "Perplexity AI, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "Raw results and a fetch tool, but QPS rises with cumulative spend from 1 on Tier 0, a user checking 100 citations a job needs higher limits, and ZDR needs a written agreement.",
      "source": "https://docs.perplexity.ai/docs/admin/rate-limits-usage-tiers.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/perplexity-search-api"
    },
    {
      "slug": "searchapi-io",
      "name": "SearchAPI.io",
      "company": "SearchApi, LLC",
      "grade": "D",
      "fit": "caveat",
      "why": "Raw SERP results, but no per-second rate is documented and monthly plans pace hourly.",
      "source": "https://www.searchapi.io/openapi/google.yaml",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/searchapi-io"
    },
    {
      "slug": "serpapi",
      "name": "SerpApi",
      "company": "SerpApi, LLC",
      "grade": "B",
      "fit": "caveat",
      "why": "Raw SERP results and free cached repeats, but plans are hourly paced and a 429 means either the hourly limit or an empty balance.",
      "source": "https://serpapi.com/search-api.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/serpapi"
    },
    {
      "slug": "serpkite",
      "name": "SerpKite",
      "company": "Anastasia Klimova, trading as SerpKite",
      "grade": "BB",
      "fit": "caveat",
      "why": "Raw results and page fetches with distinct 429 rate_limited and 503 codes, but no requests-a-second figure appears in the spec.",
      "source": "https://serpkite.com/openapi/serp-api.yaml",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/serpkite"
    },
    {
      "slug": "specstream",
      "name": "SpecStream",
      "company": "SpecStream SAS",
      "grade": "B",
      "fit": "caveat",
      "why": "A fact answer is returned only when two sites print the value or a vote rates it likely; the per-minute call limit is not published.",
      "source": "https://specstream.ai/docs/search-api.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/specstream"
    },
    {
      "slug": "tavily-mcp",
      "name": "Tavily API + MCP",
      "company": "AlphaAI Technologies Inc. dba Tavily",
      "grade": "A",
      "fit": "caveat",
      "why": "Raw results and extracts, but the free plan allows 100 requests a minute, under 5 a second, and no zero data retention option was found.",
      "source": "https://docs.tavily.com/documentation/rate-limits.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/tavily-mcp"
    },
    {
      "slug": "valyu",
      "name": "Valyu",
      "company": "Valyu.Network Ltd",
      "grade": "BB",
      "fit": "caveat",
      "why": "Raw results with URLs, but 5 requests a second on pay-as-you-go (10 on the $29 plan), billed per result, with 206 for partial failures.",
      "source": "https://docs.valyu.ai/api-reference/overview.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/valyu"
    },
    {
      "slug": "you-com-api",
      "name": "You.com APIs",
      "company": "SuSea, Inc., d/b/a you.com",
      "grade": "BB",
      "fit": "caveat",
      "why": "Raw results and contents, but rate limits depend on an unpublished tier and ZDR covers only Web Search and Answer on enterprise agreements.",
      "source": "https://you.com/docs/rate-limits.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/you-com-api"
    },
    {
      "slug": "cloudflare-web-search",
      "name": "Cloudflare Web Search API",
      "company": "Cloudflare, Inc.",
      "grade": "B",
      "fit": "unchecked",
      "why": "No rate limit for the endpoint on the pages read, so the 5 a second criterion cannot be checked from docs.",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/cloudflare-web-search"
    },
    {
      "slug": "kagi-search",
      "name": "Kagi Search API",
      "company": "Kagi Inc.",
      "grade": "C",
      "fit": "unchecked",
      "why": "No rate numbers are published and a 429 covers both rate limiting and an exhausted usage limit, so 5 a second cannot be read from the docs.",
      "source": "https://kagi.com/api/docs/_spec/openapi.yaml",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/kagi-search"
    },
    {
      "slug": "serper",
      "name": "Serper",
      "company": "Serper",
      "grade": "F",
      "fit": "unchecked",
      "why": "No rate limit is published anywhere readable; the playground needs JavaScript.",
      "confidence": "low",
      "url": "https://www.anchorterminal.com/tools/serper"
    },
    {
      "slug": "arcmira",
      "name": "Arcmira",
      "company": "Arcmira, Inc.",
      "grade": "B",
      "fit": "no",
      "why": "Can confirm only that something was said in an indexed video or podcast, not that a web URL exists.",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/arcmira"
    },
    {
      "slug": "bing-grounding",
      "name": "Grounding with Bing Search",
      "company": "Microsoft Corporation",
      "grade": "B",
      "fit": "no",
      "why": "The provider returns an answer rather than the raw source, the blocker the map names for Bing Grounding.",
      "source": "https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/bing-tools",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/bing-grounding"
    },
    {
      "slug": "grep-ai",
      "name": "Grep AI",
      "company": "Parcha Labs, Inc.",
      "grade": "B",
      "fit": "no",
      "why": "A run returns a report, not a live result per URL at 5 a second.",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/grep-ai"
    },
    {
      "slug": "serphouse",
      "name": "SERPHouse",
      "company": "Patoliya Infotech LLP",
      "grade": "E",
      "fit": "no",
      "why": "60 requests a minute is one a second, below the 5 a second the use case needs.",
      "source": "https://www.serphouse.com/docs/getting-started",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/serphouse"
    },
    {
      "slug": "tinyfish-search",
      "name": "TinyFish Search",
      "company": "Tiny Fish, Inc.",
      "grade": "B",
      "fit": "no",
      "why": "30 requests a minute per person is half a request a second, far below the 5 a second the use case needs.",
      "source": "https://docs.tinyfish.ai/search-api/reference.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/tinyfish-search"
    }
  ],
  "marks": "yes: the docs show it does the job as the success test says. caveat: it does the job with a limit an agent should know. no: it doesn't do this job. unchecked: we couldn't read it.",
  "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": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "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"
  },
  "useCase": {
    "accounts": 2,
    "after": [],
    "area": "web-data",
    "asks": [
      "do these sources exist",
      "verify this quote",
      "is this URL real and does it say that"
    ],
    "before": [
      "search.deep-research"
    ],
    "blockers": [
      "per-account rate limit of 5 a second shared across keys (DeepSeek, TinyFish 30 a minute)",
      "provider returns an answer rather than the raw source (Bing Grounding)"
    ],
    "capabilities": [
      "web.search",
      "web.fetch"
    ],
    "category": "search",
    "categoryName": "Web search APIs",
    "checked": "2026-11-12",
    "companies": {
      "fit": 4,
      "fitWithLimit": 14,
      "tagged": 68
    },
    "competition": "crowded",
    "fits": [
      "agentcore-web-search",
      "exa-mcp",
      "linkup",
      "parallel-search-api"
    ],
    "fitsWithLimit": [
      "brave-search-mcp",
      "deepseek-search-api",
      "fetch-reference-server",
      "liner-mcp",
      "mojeek",
      "newscatcher",
      "perplexity-search-api",
      "searchapi-io",
      "serpapi",
      "serpkite",
      "specstream",
      "tavily-mcp",
      "valyu",
      "you-com-api"
    ],
    "id": "search.verify-citation",
    "listings": {
      "caveat": 14,
      "no": 5,
      "notRead": 0,
      "tagged": 69,
      "unchecked": 3,
      "yes": 4
    },
    "name": "Check that a citation or claim exists",
    "status": "draft",
    "success": "For each item, a live result confirming or denying it, at a sustained rate of at least 5 a second without a rate-limit stall, and no model-written answer in place of the source.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/search.verify-citation.json",
    "weight": 6,
    "weightBasis": "2 of 44 accounts (one detailed, one vendor-aligned); weighted above its count because it is the step that makes the other research jobs trustworthy"
  }
}
