Biopharma Catalyst Mcp
Connects Claude to six free biopharma data sources (ClinicalTrials.gov, PubMed, SEC EDGAR, SEC XBRL, openFDA, Yahoo Finance) and runs forensic audits on drug catalysts. The headline tool is audit_catalyst, which takes a ticker, drug name, and sponsor, then returns a deterministic verdict (CLEAN, FLAG, BEAR_SIGNAL, BLACK_FLAG, or DISQUALIFIED) by cross-referencing trial status, FDA approval history, cash runway, insider transactions, and options IV. Built for the workflow of checking whether a catalyst story holds up. Individual tools let you query each source directly if you want to bypass the aggregator. No API keys required. Designed to compress a 2-4 hour manual research session into 30 seconds by surfacing trial terminations, amended protocols, and cash burn against what the company is saying publicly.
- GitHub stars
- 3
- tools
- 10
- auth
- Required
- transport
- STDIO
- env var
- 1
- last updated
- May 11, 2026
Tools
10 toolsPublic tool metadata for what this MCP can expose to an agent.
audit_catalystHeadline tool. Runs the full Tactical Auditor workflow against (ticker, drug). Deterministic verdict.
Headline tool. Runs the full Tactical Auditor workflow against (ticker, drug). Deterministic verdict.
No parameter schema in public metadata yet.
search_clinical_trialsPipeline + status by intervention; flags terminations, withdrawals, completed-without-readout
Pipeline + status by intervention; flags terminations, withdrawals, completed-without-readout
No parameter schema in public metadata yet.
search_pubmedRecent literature on a drug / mechanism / disease
Recent literature on a drug / mechanism / disease
No parameter schema in public metadata yet.
get_sec_filingsLast 10 filings (10-K, 10-Q, 8-K, S-1) by ticker
Last 10 filings (10-K, 10-Q, 8-K, S-1) by ticker
No parameter schema in public metadata yet.
get_xbrl_factsCash, quarterly burn, runway months, Going Concern flag
Cash, quarterly burn, runway months, Going Concern flag
No parameter schema in public metadata yet.
get_insider_transactionsRole-classified insider transactions (clinical/financial/admin), coordinated exit detection (72h window), Net Insider Sentiment ($), 10b5-1 detection
Role-classified insider transactions (clinical/financial/admin), coordinated exit detection (72h window), Net Insider Sentiment ($), 10b5-1 detection
No parameter schema in public metadata yet.
get_short_interestShort % of float, days to cover, MoM delta — feeds SHORT_INTEREST_SPIKE and SHORT_SQUEEZE_POTENTIAL signals
Short % of float, days to cover, MoM delta — feeds SHORT_INTEREST_SPIKE and SHORT_SQUEEZE_POTENTIAL signals
No parameter schema in public metadata yet.
get_protocol_snapshotTrial protocol + amendment proximity (goalpost detection)
Trial protocol + amendment proximity (goalpost detection)
No parameter schema in public metadata yet.
get_market_dataQuote + full options chain (IV, strikes, expirations)
Quote + full options chain (IV, strikes, expirations)
No parameter schema in public metadata yet.
get_fda_activityNDA/BLA submissions with decoded status (AP, CRL, WD, etc.); auto-fallback drug→sponsor
NDA/BLA submissions with decoded status (AP, CRL, WD, etc.); auto-fallback drug→sponsor
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
SEC_USER_AGENT*SEC EDGAR User-Agent header (your-app/1.0 your@email.com). Required by SEC fair-use policy.
Readme
biopharma-catalyst-mcp
A forensic biopharma research MCP server — pulls catalyst-grade signals from 6 free, authoritative sources (ClinicalTrials.gov, PubMed, SEC EDGAR, SEC XBRL companyfacts, openFDA, Yahoo Finance) and hands them to your LLM. Includes a server-side aggregator that runs the full forensic workflow in one tool call and returns a deterministic verdict.
Built for the workflow most retail biopharma analysts actually run: a ticker hits the radar, you spend 2–4 hours grinding Google Scholar, FDA pages, EDGAR, and the options chain to decide if the catalyst story holds up. This compresses that to ~30 seconds.
Details
- Repository
- github.com/yesc97/biopharma-catalyst-mcp
- Package
biopharma-catalyst-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active