sanikacentric/biolit-mcp

Citation-grounded biomedical literature review for Claude. An MCP server over PubMed, Europe PMC, NCBI Gene and UniProt, an Evidence Review agent skill, and a 50-question benchmark that measures whether answers can be trusted.
Scientists don't adopt AI research assistants that invent citations. BioLit is built around one rule: Claude may only cite papers it has actually retrieved and read in the session, and the benchmark checks that every cited PMID exists and supports its claim.
mermaid
flowchart LR
U[Scientist] --> C[Claude + Evidence Review skill]
C -- MCP --> S[BioLit server]
S --> P[PubMed E-utilities search]
S --> E[Europe PMC abstracts + citation check]
S --> G[NCBI Gene]
S --> UP[UniProt Swiss-Prot]
C --> A[Answer: claims → PMIDs]
A --> B[Benchmark: PMID exists? claim supported?]
## Tools
| Tool | Source | Returns |
| searchpubmed(query, maxresults, minyear) | NCBI E-utilities | PMIDs, titles, journals, years, publication types |
| getabstracts(pmids) | Europe PMC | Abstracts + metadata; non-existent PMIDs listed in notfound |
| lookupgene(symbol, taxonid) | NCBI Gene | Official name, chromosome, cytogenetic location, aliases, summary |
| lookupprotein(genesymbol, taxonid) | UniProt | Reviewed accession, protein name, length, function |
All tools are read-only. Production details: request timeouts, retry with exponential backoff on 429/5xx, NCBI rate limiting (3 req/s, or 10 req/s with NCBIAPIKEY), input validation, and error messages that are safe to show the model.
## Quick start
Requires Python 3.11+ and uv.
Claude Code
bash
claude mcp add biolit -- uvx --from git+https://github.com/sanikacentric/biolit-mcp biolit-mcp
mkdir -p ~/.claude/skills && cp -r skills/evidence-review ~/.claude/skills/
Claude Desktop (claudedesktopconfig.json)
json
"mcpServers": {
"biolit": {
"command": "uvx",
"args": ["--from", "git+https://github.com/sanikacentric/biolit-mcp", "biolit-mcp"],
"env": { "NCBIEMAIL": "you@example.com" }
Remote (Streamable HTTP): biolit-mcp --transport streamable-http
Optional environment variables: NCBIAPIKEY (higher rate limit), NCBIEMAIL (recommended by NCBI).
Then ask: "What is the evidence that lecanemab slows cognitive decline in early Alzheimer's disease?"
## Evidence Review skill
skills/evidence-review/SKILL.md gives Claude a scientist's workflow: resolve entities → run focused searches → read abstracts → write one claim per sentence with PMIDs → self-check every citation before answering. The output separates the bottom line, evidence, strength & gaps, and references.
## Benchmark
evals/ runs 50 questions with and without the BioLit tools:
30 fact questions: UniProt accession + chromosome for well-characterized human genes, scored exactly.
20 literature questions: across oncology, cardiometabolic, neuro, gene therapy and structural biology. Every cited PMID is checked live against PubMed, and an LLM judge decides whether the cited abstracts support each claim.