A side-by-side look at the Biolit and Ncbi MCP Server MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Biolit for biology, medicine and bioinformatics work as a local process; choose Ncbi MCP Server for biology, medicine and bioinformatics. You can also run both side by side in one mcpServers block.
ANTHROPIC_API_KEY, OPENAI_API_KEY, LLM_PROVIDER, LLM_MODEL, CORE_API_KEY, BIOLIT_CUSTOM_RESOLVERS.run_pipeline, fetch_pubmed_metadata, fetch_geo_record.search_pubmed, get_article_details, search_mesh_terms.Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Biology, Medicine and Bioinformatics | Biology, Medicine and Bioinformatics |
| Quality signal | 53/100 · Good | 47/100 · Fair |
| Install command | Confirmed | Not confirmed yet |
| Transport | Local subprocess (stdio) | — |
| Auth | Not declared | No auth required |
| Pricing | Not declared | Free |
| Required env vars | ANTHROPIC_API_KEYOPENAI_API_KEYLLM_PROVIDERLLM_MODELCORE_API_KEYBIOLIT_CUSTOM_RESOLVERS | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 2 | 13 |
| Directory activity | 1 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 12 | 5 |
| Full listing | View Biolit | View Ncbi MCP Server |
run_pipelineFetch, optionally screen, and optionally extract a mixed list of PMIDs, DOIs, and/or GEO accessions; write results CSV (and optionally a `.md` summary when `markdown=True`). Accepts `ids` (comma-separated), `bib_path` (`.bib` file), or `ids_file` (plain-text identifier file). Pass `sections` (comma…fetch_pubmed_metadataFetch PubMed metadata by PMIDfetch_geo_recordFetch and parse a GEO record by accessionfetch_fulltextRetrieve full text for a PMID (6-step chain)fetch_geo_fulltextRetrieve full text for a GEO accession via its linked PMIDsfetch_supplementaryRetrieve & extract text from a paper's supplementary files (supplementary methods, tables) via Europe PMCscreen_paperLLM relevance screen given pre-fetched textextract_fieldsStructured field extraction given pre-fetched textresolve_doiResolve a DOI to PMID + PMCID via the NCBI ID Converterlookup_s2_pdfCheck whether Semantic Scholar has an open-access PDF for a DOIread_pmids_from_emlParse PMIDs from a PubMed alert `.eml` fileget_versionReturn the installed biolit package versionsearch_pubmedPrimary search tool for PubMed databaseget_article_detailsFetch complete information for specific articlessearch_mesh_termsFind standardized Medical Subject Headingsget_related_articlesDiscover articles related to a specific paperadvanced_searchComplex searches with multiple criteriaPaste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
{
"mcpServers": {
"biolit": {
"command": "uvx",
"args": [
"biolit"
],
"env": {
"ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
"OPENAI_API_KEY": "YOUR_OPENAI_API_KEY_HERE",
"LLM_PROVIDER": "YOUR_LLM_PROVIDER_HERE",
"LLM_MODEL": "YOUR_LLM_MODEL_HERE",
"CORE_API_KEY": "YOUR_CORE_API_KEY_HERE",
"BIOLIT_CUSTOM_RESOLVERS": "YOUR_BIOLIT_CUSTOM_RESOLVERS_HERE"
}
}
}
}
No confirmed install command for Ncbi MCP Server yet — follow the setup steps linked from its listing page rather than a guessed package name.