Skip to content
Psilocybin Research logo

Psilocybin Research MCP server

Which MCP servers are Psilocybin Research's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-11-03

← Back to Psilocybin Research

Whose server it is
  • Registry namecom.psilocybin-research/researchverified in the MCP registry

The registry name sits under psilocybin-research.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-11-03
  • Stateanswerschecked 2026-11-03
  • Tools8
  • Server calls itselfpsilocybin-research
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-11-03 the server answered initialize and tools/list without a sign-in. First answer in 519 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 3 of the 7 days it takes to judge reliability.

Once connected

  • Parameters are untyped or undescribed in 3 of 9 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 3, the first on 2026-11-03
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer706 ms
  • Space in an agent's context≈ 1,371 tokensthe definitions of all its tools (9), which an agent carries on every turn
  • Tool definitionsA · 94 of 100
  • Typed results9 of 9 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 3 of 9

What an agent can do with it

  • not sure · search psilocybin publications by year, topic and study type
  • not sure · find recruiting psilocybin clinical trials on a country map
  • can do · export and cite selected publication records

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers8 tools · read 2026-11-03
  • search

    Find up to 20 relevant bibliographic records using keywords or identifiers; use fetch with a returned ID for complete public metadata. This bounded discovery list is not an exhaustive export. Use get_dataset_downloads for the entire…

  • fetch

    Retrieve the public metadata document for one search ID, with source links, publication status and citation. The document is bibliographic metadata, not the publisher full text or abstract.

  • search_publications

    Search public publications, preprints and trial-registration records with explicit filters, total counts and pagination. Query and author are keyword searches; journal/topic/source/status filters use stored labels. Preserve distinct IDs…

  • search_trials

    Find registered clinical trials by keywords or exact country, sponsor, phase, condition or registry status. Returns bounded pages and registry observation dates. Registry statements and recruitment status are not completed treatment…

  • get_citation

    Retrieve citation text, BibTeX and RIS for one visible record ID. Retains preprint/registration status. Check the original source before citing.

  • get_citation_relationships

    Return a bounded set of explicit reference DOIs and indexed citing records for a visible record ID. These source-derived links are incomplete and are not proof of scientific support, criticism or trial/result identity.

  • get_annual_statistics

    Retrieve catalogue-wide annual/status counts, missing-year totals, UTC generation time and source revision. No filters. Counts are indexed records, not independent studies or participants; current-year coverage is partial.

  • get_dataset_downloads

    Retrieve the current completed dataset manifest with eleven exact download URLs, SHA-256 checksums, byte sizes, count, UTC and source revision. Use for full SQLite/CSV/JSON, citations, ZIP, compact JSON, titles/years TXT or frozen…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "research": {
      "type": "http",
      "url": "https://psilocybin-research.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http psilocybin-research https://psilocybin-research.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://psilocybin-research.com/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.