Autosearch

uk.exatoshiPublished by exatoshi.ukOfficial publisherv1.0.0Updated Oct 27, 2026

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

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingKnowledge & MemoryAI & ML

Overview

AI-generated overview

Remote MCP server that lets an assistant launch AI research runs, poll their status, fetch generated IMRAD papers, and verify DOIs via Crossref.

What you can do
  • Launch AI scientific research runs and receive a run ID to poll
  • Check run status, frontier score, experiment count and summary
  • Retrieve a completed run's paper as markdown, JSON metadata or a PDF link
  • Verify DOIs through Crossref for validity, title, authors, year and journal
  • Search peer-reviewed evidence across academic sources without a full run
  • List the authenticated user's latest runs with status and frontier score
When to use it
Useful when an assistant needs to produce or support literature-backed research, such as PRISMA-style systematic reviews, and wants verified citations rather than invented references. Also handy for quick evidence searches or DOI checks without running a full study.
Requirements
A remote endpoint at exatoshi.uk over streamable HTTP, with no local package. Requires an AutoSearch API key sent in the x-api-key header; the key is free from the provider's account page. Network access to the provider is needed.
Before you install
The API key is a secret sent in the x-api-key header, so keep it out of shared logs and transcripts. Research runs are created on the provider's service and tied to your account, and run data, queries and generated papers are sent to that third party. DOI verification depends on Crossref data.

Installation

In SourceWeft

  1. Open Autosearch in the dashboard and add it to a workspace.
  2. Connect x-api-key credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/uk.exatoshi%2Fautosearch/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "autosearch": {
      "type": "http",
      "url": "https://exatoshi.uk/mcp",
      "headers": {
        "x-api-key": "<YOUR_API_KEY>"
      }
    }
  }
}

Tools

6

autosearch_run_research

Launch an AI scientific research run. Returns run_id immediately. Use get_run_status to poll.

Parametersdepthpromptrequired

autosearch_get_run_status

Get the current status of a research run. Returns status, frontier_score, n_experiments, summary.

Parametersrun_idrequired

autosearch_get_run_paper

Get the generated paper for a completed run. Returns markdown, JSON metadata, or PDF download URL.

Parametersformatrun_idrequired

autosearch_verify_doi

Verify a DOI via Crossref. Returns validity, title, authors, year, journal.

Parametersdoirequired

autosearch_search_evidence

Search peer-reviewed evidence across academic sources without launching a full research run. Returns top N papers with metadata.

Parameterslimitqueryrequiredsources

autosearch_list_my_runs

List the authenticated user latest research runs with status and frontier score.

Parameterslimit

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

72% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts

    Publish an icon in the registry entry.

  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.