{
  "listings": [
    {
      "slug": "liner-mcp",
      "name": "Liner Search MCP",
      "company": "Liner",
      "grade": "E",
      "fit": "yes",
      "why": "Deep Research Agent streams SSE with inline citation chunks at $200 per 1,000 runs, but there is no task id to poll, so an MCP client must hold the stream open.",
      "source": "https://liner.com/llms-full.txt",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/liner-mcp"
    },
    {
      "slug": "linkup",
      "name": "Linkup",
      "company": "Linkup Technologies SAS",
      "grade": "B",
      "fit": "yes",
      "why": "POST /research returns a task id at once, GET /research/:id polls status, reasoningDepth sets a fixed price per run, and 402 carries x402 details.",
      "source": "https://docs.linkup.so/pages/documentation/endpoints/research/post.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/linkup"
    },
    {
      "slug": "you-com-api",
      "name": "You.com APIs",
      "company": "SuSea, Inc., d/b/a you.com",
      "grade": "BB",
      "fit": "yes",
      "why": "Research API with background true returns a task_id, GET polls status and a stream endpoint sends SSE progress; prices by research_effort are listed.",
      "source": "https://you.com/docs/guides/research/background-requests.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/you-com-api"
    },
    {
      "slug": "bing-grounding",
      "name": "Grounding with Bing Search",
      "company": "Microsoft Corporation",
      "grade": "B",
      "fit": "caveat",
      "why": "One Responses run returns a grounded answer with url_citation annotations, synchronously, at $14 per 1,000 tool calls plus model tokens; no async research task or report mode.",
      "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": "brave-search-mcp",
      "name": "Brave Search API + MCP",
      "company": "Brave Software, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "An Answers service with citations is listed, but it answers synchronously with no task id, and the Summarizer it replaced returned 'No web results found' on free keys until a fix.",
      "source": "https://api-dashboard.search.brave.com/llms.txt",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/brave-search-mcp"
    },
    {
      "slug": "exa-mcp",
      "name": "Exa API + MCP",
      "company": "Exa Labs Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "Agent runs return an id, poll or stream SSE events, and output.grounding carries citations; price is by effort, but no budget field appears in the quickstart read.",
      "source": "https://exa.ai/docs/agent/quickstart.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/exa-mcp"
    },
    {
      "slug": "grep-ai",
      "name": "Grep AI",
      "company": "Parcha Labs, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "Runs are async with a run id, timeline, webhook_url, Idempotency-Key and max_cost_usd, but the cost floor depends on effort ($0.50 low, $2.50 medium, $5 high per the listing) and API access is sold on Pro and Ultra plans.",
      "source": "https://api.grep.ai/api/v2/openapi.json",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/grep-ai"
    },
    {
      "slug": "newscatcher",
      "name": "NewsCatcher",
      "company": "NewsCatcher, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "Agent runs research events or companies in the background and return a table, not a cited prose report, at 1,000 to 6,000 credits a run.",
      "source": "https://www.newscatcherapi.com/docs/get-started/credits-and-pricing",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/newscatcher"
    },
    {
      "slug": "parallel-search-api",
      "name": "Parallel Search and Task APIs",
      "company": "Parallel Web Systems Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "Task runs have a run_id, completed or failed status with errors, webhooks and SSE, with fixed prices by processor, but the SDKs retry creation on 429 with no idempotency key (listing weakness).",
      "source": "https://docs.parallel.ai/task-api/guides/execute-task-run.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/parallel-search-api"
    },
    {
      "slug": "perplexity-search-api",
      "name": "Perplexity Search API",
      "company": "Perplexity AI, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "The Agent API's web_search tool writes a cited answer synchronously; the MCP perplexity_research tool buffered the whole stream and timed out clients until a fix in July 2026.",
      "source": "https://docs.perplexity.ai/docs/getting-started/integrations/mcp-server.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/perplexity-search-api"
    },
    {
      "slug": "serpkite",
      "name": "SerpKite",
      "company": "Anastasia Klimova, trading as SerpKite",
      "grade": "BB",
      "fit": "caveat",
      "why": "/v1/research returns 202 and is polled at GET /v1/research/{id}, with fixed prices of 30, 75 or 200 credits, but the vendor's record is six weeks of status monitoring.",
      "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": "Deep Search builds rows with a source page per value after a quoted, approved price and an idempotency key; it is a list builder, not a cited prose report.",
      "source": "https://specstream.ai/llms.txt",
      "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": "/research is async with a request_id and status, a stream option and model mini, pro or auto at 4 to 250 credits, but over MCP it hung forever when model was unspecified.",
      "source": "https://docs.tavily.com/documentation/api-reference/endpoint/research.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/tavily-mcp"
    },
    {
      "slug": "tinyfish-search",
      "name": "TinyFish Search",
      "company": "Tiny Fish, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "Research runs stream SSE events (sources_searched, source_fetched, final_result with citations) with a reconnectable events endpoint and cancel, but no price or cost cap appears in the reference and deep runs take 5 to 45 minutes.",
      "source": "https://docs.tinyfish.ai/research-api/reference.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/tinyfish-search"
    },
    {
      "slug": "valyu",
      "name": "Valyu",
      "company": "Valyu.Network Ltd",
      "grade": "BB",
      "fit": "caveat",
      "why": "DeepResearch creates a task with deepresearch_id to poll or a webhook, fixed credits per mode from 8 to 2,500 and hard time limits, with citations carrying passages; but task creation has no idempotency key (listing weakness).",
      "source": "https://docs.valyu.ai/guides/deepresearch.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/valyu"
    },
    {
      "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": "no",
      "why": "Returns ranked results in one call. Cited answers are a separate Web Answer connector, not this listing.",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/agentcore-web-search"
    },
    {
      "slug": "arcmira",
      "name": "Arcmira",
      "company": "Arcmira, Inc.",
      "grade": "B",
      "fit": "no",
      "why": "No research or report endpoint; an investment research workflow is a guide for the agent, not a hosted task.",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/arcmira"
    },
    {
      "slug": "cloudflare-web-search",
      "name": "Cloudflare Web Search API",
      "company": "Cloudflare, Inc.",
      "grade": "B",
      "fit": "no",
      "why": "No research or answer mode; the response is a results array.",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/cloudflare-web-search"
    },
    {
      "slug": "deepseek-search-api",
      "name": "DeepSeek Search and Fetch API",
      "company": "Hangzhou DeepSeek Artificial Intelligence Co., Ltd.",
      "grade": "C",
      "fit": "no",
      "why": "Two endpoints, search and fetch; no research or answer mode is listed.",
      "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": "no",
      "why": "No research mode.",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/fetch-reference-server"
    },
    {
      "slug": "kagi-search",
      "name": "Kagi Search API",
      "company": "Kagi Inc.",
      "grade": "C",
      "fit": "no",
      "why": "No research or answer endpoint in the OpenAPI document.",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/kagi-search"
    },
    {
      "slug": "mojeek",
      "name": "Mojeek Web Search API",
      "company": "Mojeek Limited",
      "grade": "F",
      "fit": "no",
      "why": "No research or answer mode.",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/mojeek"
    },
    {
      "slug": "searchapi-io",
      "name": "SearchAPI.io",
      "company": "SearchApi, LLC",
      "grade": "D",
      "fit": "no",
      "why": "No research or answer mode.",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/searchapi-io"
    },
    {
      "slug": "serpapi",
      "name": "SerpApi",
      "company": "SerpApi, LLC",
      "grade": "B",
      "fit": "no",
      "why": "No research mode; Google AI Mode results are scraped, not written.",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/serpapi"
    },
    {
      "slug": "serper",
      "name": "Serper",
      "company": "Serper",
      "grade": "F",
      "fit": "no",
      "why": "No research or answer mode.",
      "confidence": "low",
      "url": "https://www.anchorterminal.com/tools/serper"
    },
    {
      "slug": "serphouse",
      "name": "SERPHouse",
      "company": "Patoliya Infotech LLP",
      "grade": "E",
      "fit": "no",
      "why": "No research or answer mode.",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/serphouse"
    }
  ],
  "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": 6,
    "after": [
      "document-generation.report",
      "memory.store"
    ],
    "area": "web-data",
    "asks": [
      "research X thoroughly and write it up",
      "compare these companies with sources",
      "detailed look on X"
    ],
    "before": [
      "search.ground-fact"
    ],
    "blockers": [
      "research tool blocks for minutes and the MCP client times out (Perplexity, Tavily)",
      "no idempotency so a retry starts and bills a second task",
      "minimum spend per run of $0.50 or more (Grep AI)"
    ],
    "capabilities": [
      "search.research",
      "search.answer"
    ],
    "category": "search",
    "categoryName": "Web search APIs",
    "checked": "2026-11-12",
    "companies": {
      "fit": 3,
      "fitWithLimit": 12,
      "tagged": 19
    },
    "competition": "few",
    "fits": [
      "liner-mcp",
      "linkup",
      "you-com-api"
    ],
    "fitsWithLimit": [
      "bing-grounding",
      "brave-search-mcp",
      "exa-mcp",
      "grep-ai",
      "newscatcher",
      "parallel-search-api",
      "perplexity-search-api",
      "serpkite",
      "specstream",
      "tavily-mcp",
      "tinyfish-search",
      "valyu"
    ],
    "id": "search.deep-research",
    "listings": {
      "caveat": 12,
      "no": 11,
      "notRead": 0,
      "tagged": 20,
      "unchecked": 0,
      "yes": 3
    },
    "name": "Hand off a research question for a cited report",
    "status": "draft",
    "success": "A report or answer with inline citations, delivered by an async task id or a streamed response, with the cost known before the run. Measured: the cited URLs resolve, and a streamed response does not time out the MCP client.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/search.deep-research.json",
    "weight": 10,
    "weightBasis": "6 of 44 accounts: a platform running 10-plus searches and 100-plus fetches a job, three MCP issues where research tools hung or timed out, Kagi and Perplexity research tool reports"
  }
}
