MCP ServerSTDIOOfficialv0.1.25

Rachadele Biolit MCP Server

Screen and extract data from biomedical literature across PubMed, GEO, and preprints using LLM-assisted analysis. Built for researchers and developers automating systematic reviews, meta-analyses, and literature curation workflows.

io.github.rachadele/biolit

Hosted URL

Local install

Transport

STDIO

Auth

No auth required

What the Rachadele Biolit MCP server does

How models use it and what it is built for.

Screen and extract data from biomedical literature across PubMed, GEO, and preprints using LLM-assisted analysis. Built for researchers and developers automating systematic reviews, meta-analyses, and literature curation workflows.

Connect to Rachadele Biolit

Local install — runs as a subprocess.

uvx biolit==0.1.25

Environment variables

Configuration this server reads at startup.

  • ANTHROPIC_API_KEYSecret

    Anthropic API key (required when using the default Anthropic provider)

  • OPENAI_API_KEYSecret

    OpenAI API key (required when using LLM_PROVIDER=openai)

  • LLM_PROVIDER

    LLM provider: anthropic (default), openai, or ollama

  • LLM_MODEL

    Model name override (e.g. claude-sonnet-4-6, gpt-4o)

  • SEMANTIC_SCHOLAR_API_KEYSecret

    Semantic Scholar API key for higher rate limits on citation lookup (optional)

  • UNPAYWALL_EMAIL

    Email address for Unpaywall API access to improve PDF retrieval (optional)

Resources

Where to find authoritative docs and source for Rachadele Biolit.

Example prompts for Rachadele Biolit

Paste any of these into Agent Studio after connecting Rachadele Biolit.

  • Search PubMed for papers on CRISPR gene therapy and screen abstracts for clinical trial data
  • Extract gene expression datasets from GEO matching my inclusion criteria using semantic filtering
  • Retrieve preprint metadata and PDFs for papers on mRNA vaccine mechanisms published in the last 6 months
  • Compare citation networks across PubMed and Semantic Scholar for papers on immunotherapy resistance

Rachadele Biolit MCP server — FAQ

Common questions about connecting and running Rachadele Biolit.

  • What LLM providers does biolit support?

    Biolit supports Anthropic (default), OpenAI, and Ollama. Set LLM_PROVIDER and optionally override the model name with LLM_MODEL (e.g., gpt-4o or claude-sonnet-4-6).

  • Do I need API keys to use biolit?

    Yes, you need either ANTHROPIC_API_KEY or OPENAI_API_KEY depending on your LLM_PROVIDER. SEMANTIC_SCHOLAR_API_KEY and UNPAYWALL_EMAIL are optional but recommended for higher rate limits and better PDF retrieval.

  • What data sources can biolit query?

    Biolit integrates PubMed, GEO (Gene Expression Omnibus), preprint servers, and Semantic Scholar for citation lookup. It can retrieve abstracts, metadata, and PDFs where available.

  • How does the LLM-assisted screening work?

    The server uses your configured LLM to analyze and filter literature based on your criteria—screening abstracts, extracting structured data, and ranking results by relevance without manual review of every paper.

  • Can I use biolit offline or with a local model?

    Yes, set LLM_PROVIDER=ollama to use a local LLM. You'll still need internet access to query PubMed, GEO, and preprint APIs, but LLM inference runs locally.

Skip the local setup — run MCP in your browser

MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 30+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.

Open Agent Studio

Related servers

More on MCP Playground