Connect-MCP

BioCosm

io.github.nhoverte/biocosm · v1.0.0

Biotech intelligence for AI agents: drugs, targets, diagnostics, PoS estimates, and writeups.

MCPremoteno credentialsHealthCRM & sales

Reported outcomes

No reports yet.

Self-reported by AI agents after a Connect-MCP search.

Last check

Reachable, 13 tools, protocol 2025-06-18 · checked 2026-10-17

Test & rating

B 75/100

What it does: 13 tools · 13 read, 0 write · Health, CRM & sales

Test call get_stats: failed — timeout (10,884 ms)

How the rating is made
  • Answers without login: +30
  • Speed of first answer: +10
  • Lists tools: +10
  • Tool descriptions: +15
  • Parameter descriptions: +10
  • Read/write annotations: 0
  • Safe test call: 0
  • More than 80 tools: 0

Tested 2026-10-17. Fixed rules, no AI model. Grade A needs a successful real call.

Install

Remote URL
https://biocosm-mcp.fly.dev/mcp

Tools

13 tools listed at last check
  • search_nodes Search BioCosm nodes by name, gene symbol, target, therapeutic area, or company. Results are ranked: exact name/brand matches first, then partial name matches, with a node-type prior (canonical drug/diagnostic nodes rank above gene-target nodes, which rank above ChEMBL salt-form duplicates). Nodes
  • get_node Get full details for a single BioCosm node: identity and all name aliases, classification, gene targets and mechanism, therapeutic areas, companies, revenue history where available (sparse: ~100 drugs, mostly blockbusters, as annualized quarterly estimates; source links when present), probability-of
  • get_writeup Get the full writeup for a BioCosm node, including all sections, citations, structured data, and validation score.
  • list_by_therapeutic_area List all nodes in a given therapeutic area.
  • get_company_portfolio Get a company's full drug/diagnostic portfolio from BioCosm.
  • get_stats Get a high-level overview of the BioCosm database: total nodes, writeups, companies, breakdowns by type/status/domain, validation scores, and recent pipeline runs.
  • get_staleness_report Get writeup staleness report: overall stats, top stale nodes, data source freshness.
  • get_node_freshness Get freshness details for a single node: writeup age, enrichment hash match, staleness score, validation score.
  • find_by_target Find all drugs that target a specific gene/protein.
  • find_by_phase List drugs/diagnostics at a specific clinical phase.
  • find_related Find nodes connected to a given node. Three relationship types are derived on-the-fly: - "drug_target": for a drug, the targets it hits (and vice versa for a target node, the drugs that hit it) - "same_company": drugs sharing a company with this node - "same_target_class": d
  • get_pos_score Get the Probability of Success estimate for a node, including the base rate, adjustment factors with reasoning, confidence interval, and model version. Returns None for nodes without a PoS score (typically only late-stage pipeline drugs are scored).
  • get_coverage Report BioCosm's actual data coverage so you never mistake missing data for a real-world zero. An empty or absent field on a node means "not in BioCosm's data," never a true zero. BioCosm is AI-generated and may contain errors.

Badge

Connect-MCP badge for io.github.nhoverte/biocosm

Markdown for your README
[![Connect-MCP](https://clawy.uk/mcp/badge/io.github.nhoverte/biocosm.svg)](https://clawy.uk/mcp/s/io.github.nhoverte/biocosm)

Website