Hand off a research question for a cited report
Two or three companies' docs show a full fit.
What counts as done
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, for our own tests: the cited URLs resolve, and a streamed response does not time out the MCP client. No docs we read state these figures, so they don't count against a listing here.
How agents ask for it: research X thoroughly and write it up
, compare these companies with sources
, detailed look on X
Does the job 3
The docs show it meets the test above, and nothing we read says otherwise.
| Listing | Why |
|---|---|
| Liner Search MCP E Liner | 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 |
| Linkup B Linkup Technologies SAS | 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 |
| You.com APIs BB SuSea, Inc., d/b/a you.com | 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 |
Does the job, with a limit 12
It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.
| Listing | Why |
|---|---|
| Grounding with Bing Search B Microsoft Corporation | 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 |
| Brave Search API + MCP B Brave Software, Inc. | 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 |
| Exa API + MCP B Exa Labs Inc. | 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 |
| Grep AI B Parcha Labs, Inc. | 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 |
| NewsCatcher B NewsCatcher, Inc. | 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 |
| Parallel Search and Task APIs BB Parallel Web Systems Inc. | 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 |
| Perplexity Search API BB Perplexity AI, Inc. | 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 |
| SerpKite BB Anastasia Klimova, trading as SerpKite | /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 |
| SpecStream B SpecStream SAS | 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 |
| Tavily API + MCP A AlphaAI Technologies Inc. dba Tavily | /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 |
| TinyFish Search B Tiny Fish, Inc. | 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 |
| Valyu BB Valyu.Network Ltd | 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 |
Doesn't do this job 11
Listings in the category that do something else, with the reason.
| Listing | Why |
|---|---|
| Web Search Tool on Amazon Bedrock AgentCore BB Amazon Web Services, Inc. (regional AWS entities by account location) | Returns ranked results in one call. Cited answers are a separate Web Answer connector, not this listing. |
| Arcmira B Arcmira, Inc. | No research or report endpoint; an investment research workflow is a guide for the agent, not a hosted task. |
| Cloudflare Web Search API B Cloudflare, Inc. | No research or answer mode; the response is a results array. |
| DeepSeek Search and Fetch API C Hangzhou DeepSeek Artificial Intelligence Co., Ltd. | Two endpoints, search and fetch; no research or answer mode is listed. |
| Fetch (MCP reference server) B Model Context Protocol, a Series of LF Projects, LLC | No research mode. |
| Kagi Search API C Kagi Inc. | No research or answer endpoint in the OpenAPI document. |
| Mojeek Web Search API F Mojeek Limited | No research or answer mode. |
| SearchAPI.io D SearchApi, LLC | No research or answer mode. |
| SerpApi B SerpApi, LLC | No research mode; Google AI Mode results are scraped, not written. |
| Serper F Serper | No research or answer mode. |
| SERPHouse E Patoliya Infotech LLP | No research or answer mode. |
What stops agents finishing
- 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)
Around it
Before: search.ground-fact. After: document-generation.report, memory.store.
Where this comes from
Weight 10 of 100 in Web search APIs: 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
The same as data: /api/v1/use-cases/search.deep-research.json, or the MCP tool get_use_case with id search.deep-research. Other jobs in this category: /api/v1/niches?category=search.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.