Biolit MCP Server

LLM-assisted biomedical literature screening and structured extraction. Accepts PubMed alert emails and mixed lists of PMIDs, DOIs, and GEO accessions in any combination. Retrieves full text from PMC, Europe PMC, bioRxiv/medRxiv, Unpaywall, and Semantic Scholar. Supports multiple LLM providers and exposes all functionality as an MCP server. Its 12 documented tools cover geo, fulltext.

People connecting maps & location tools to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-08-22 · ★ 2 · #16 OF 56 MAINTAINED MAPS & LOCATION · VERIFIED 2026-08-25

Python servers · how we verify → /methodology

01 · Install Biolit

before you install - you'll need

Set BIOLIT_LANDING_USER_AGENT, BIOLIT_JS_SHELL_CHAR_THRESHOLD, BIOLIT_CUSTOM_RESOLVERS, ZOTERO_API_KEY, ZOTERO_USER_ID, BIOLIT_LOCAL_PDF_DIR before connecting. BIOLIT_BIBTEX, BIOLIT_BIBTEX_PRIORITY, ZOTERO_PRIORITY, ZOTERO_DATA_DIR, BIOLIT_LOCAL_PDF_PRIORITY are optional or environment-specific per the README.

Claude Code

claude mcp add rachadele-biolit -- uvx biolit

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "rachadele-biolit": {
      "command": "uvx",
      "args": [
        "biolit"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license no standard license detected - usage rights unclear; check the repo before commercial use

pypi package biolit - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.rachadele is GitHub-verified and matches the repo owner

03 · What Biolit can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can fetch and parse a GEO record by accession, retrieve full text for a PMID (6-step chain), retrieve full text for a GEO accession via its linked PMIDs, and retrieve & extract text from a paper's supplementary files (supplementary methods, tables) via Europe PMC.

Capability map

Tools grouped from the project's README - what Biolit lets an agent do.

read & search

8 tools - e.g. Fetch PubMed metadata by PMID; Fetch and parse a GEO record by accession; Retrieve full text for a PMID (6-step chain)

fetch_pubmed_metadata · fetch_geo_record · fetch_fulltext · fetch_geo_fulltext · fetch_supplementary · lookup_s2_pdf…

run & execute

1 tool - e.g. Fetch, optionally screen, and optionally extract a mixed list of PMIDs, DOIs, and/or GEO accessions; write results CSV (and optionally a .md summary when markdo

run_pipeline

Screen

1 tool - e.g. LLM relevance screen given pre-fetched text

screen_paper

Extract

1 tool - e.g. Structured field extraction given pre-fetched text

extract_fields

Resolve

1 tool - e.g. Resolve a DOI to PMID + PMCID via the NCBI ID Converter

resolve_doi

04 · Who maintains Biolit

biolit is maintained by rachadele. It's the only MCP server we track from this author; the repo dates to Mar 2026.

05 · Facts

repository: github.com/rachadele/biolit
category: maps & location - ranked #16 of 56 actively-maintained maps & location servers as of 2026-08-25.
registry: io.github.rachadele/biolit (active, first published 2026-04-01)
packages: pypi:biolit

06 · Biolit FAQ

Is Biolit still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-22. We re-verify nightly.

What can Biolit do?

How do I install Biolit?

Run `uvx biolit`. The README documents 11 environment variables (BIOLIT_LANDING_USER_AGENT, BIOLIT_JS_SHELL_CHAR_THRESHOLD, BIOLIT_CUSTOM_RESOLVERS…) to set first. Set BIOLIT_LANDING_USER_AGENT, BIOLIT_JS_SHELL_CHAR_THRESHOLD, BIOLIT_CUSTOM_RESOLVERS, ZOTERO_API_KEY, ZOTERO_USER_ID, BIOLIT_LOCAL_PDF_DIR before connecting. BIOLIT_BIBTEX, BIOLIT_BIBTEX_PRIORITY, ZOTERO_PRIORITY, ZOTERO_DATA_DIR, BIOLIT_LOCAL_PDF_PRIORITY are optional or environment-specific per the README. You can also paste the ready-made client config above.

Does Biolit run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Biolit

Alternatives to Biolit

Maintained maps & location servers if Biolit isn't the fit.

More maps & location MCP servers · Korean Secondary Learning Map MCP · Vedurstofa MCP · AI Readiness Kit · FreightUtils MCP Server · Spec Left

More Python MCP servers · Zoekt MCP · Pynet MCP Bridge · Lingua Universale MCP Server · Credit Optimizer v5 for Manus AI · Doc Pull · see all