mcpbeat Sign in

Autosearch MCP Server

answering

Autosearch is answering right now. Last checked moments ago. It exposes 6 tools.

PRISMA 2020 systematic reviews as MCP tools - verified citations, IMRAD papers

Uptime history 52 days of history
52 days agonow
100.0%
Uptime 24h
92 of 92 checks
6
Tools
read from the server
282 ms
Response time
average over 24h
open, no key
Access
streamable-http

Nothing serious here today

Today is the operative word: we check Autosearch every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 0 min ago.

run in your terminal
claude mcp add autosearch --transport http https://exatoshi.uk/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "autosearch": {
      "url": "https://exatoshi.uk/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.autosearch]
url = "https://exatoshi.uk/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "autosearch": {
      "url": "https://exatoshi.uk/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "autosearch": {
      "url": "https://exatoshi.uk/mcp"
    }
  }
}

Available tools 6

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

autosearch
autosearch_get_run_paper
Get the generated paper for a completed run. Returns markdown, JSON metadata, or PDF download URL.
autosearch_get_run_status
Get the current status of a research run. Returns status, frontier_score, n_experiments, summary.
autosearch_list_my_runs
List the authenticated user latest research runs with status and frontier score.
autosearch_run_research
Launch an AI scientific research run. Returns run_id immediately. Use get_run_status to poll.
autosearch_search_evidence
Search peer-reviewed evidence across academic sources without launching a full research run. Returns top N papers with metadata.
autosearch_verify_doi
Verify a DOI via Crossref. Returns validity, title, authors, year, journal.

Endpoints

URLTransportStateLatencyChecked
https://exatoshi.uk/mcp streamable-http answering 278 ms 0 min ago

Alternatives to Autosearch

same job, measured the same way
prismAId MCP
by open-and-sustainable

MCP server for prismAId AI-assisted systematic reviews and protocol conformance checking.

local only
Semantic Scholar MCP Server
by smaniches

MCP server for the Semantic Scholar API: search 200M+ papers, citations, authors, recommendations.

1 042 installs/wk local only
Vivory Verification Gateway
by jayjodev

98 MCP tools for verifiable AI: citations, law, KYB, peer review, forecast, media provenance.

73 installs/wk local only
WireTensors
by wiretensors

Neutral, verified AI tool reviews — search, compare and get recommendations across 260+ tools.

6 tools answering
Bounded Tools MCP
by bounded-systems

Read-only MCP server over bounded.tools's Sigstore-verified static API (stdio).

14 installs/wk local only
ScrapeNest
by scrapenest

Web search, scraping, RAG answers with citations, and translation as MCP tools.

answering
Semanticscholar
by smaboundless

Search 200M+ papers, authors, citations, and recommendations via Semantic Scholar

35 installs/wk local only
Verifa
by verifa-solutions

Identity verification, document checks, sanctions/PEP screening and case review as agent tools.

21 installs/wk answering

Autosearch — questions

Answers built from our own checks of this server.

What can Autosearch do?
It exposes 6 tools, read directly from the server on our last check. Among them: autosearch_get_run_paper, autosearch_get_run_status, autosearch_list_my_runs, autosearch_run_research, autosearch_search_evidence, autosearch_verify_doi. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Autosearch working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 282 ms. The bar chart above shows every period we have measured.
How do I connect Autosearch?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Autosearch need an API key?
No. Autosearch completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 6 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Autosearch?
It answers our handshake in 282 ms on average, which is faster than 57% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.