Which integrations are available for this server?

Searches PubMed for scientific publications related to drugs and clinical trials, returning results with PMID links.

de en es ja ko ru zh

drug-pipeline-mcp

by DasClown

Overview Schema Related Servers Score Discussions

Remote

💊 drug-pipeline-mcp

Tests Docker Smithery Python 3.10+ License: MIT PyPI GitHub stars

Pharmaceutical R&D Pipeline Intelligence for AI Agents — a lightweight MCP server that aggregates clinical trial data, FDA/EMA approvals, safety surveillance (FAERS), drug labels, patents, drug interactions, recalls, and publications through a unified API. Every output includes a verifiable source identifier (NCT ID, FDA Application Number, or PMID).

Not a replacement for IQVIA/EvaluatePharma. A real-time, publicly accessible intelligence layer that complements subscription databases.

Quick Start

pip install git+https://github.com/DasClown/drug-pipeline-mcp.git

# Start MCP server (stdio)
drug-pipeline

# Or HTTP mode for remote access
pip install drug-pipeline-mcp[http]
drug-pipeline --http --port 8081

Or deploy via Smithery — one click, no config.

Related MCP server: aria-mcp-server

Tools (28)

Tool	What it does	Data Source
`search_trials`	Search clinical trials by condition, phase, status, sponsor	ClinicalTrials.gov
`get_trial_detail`	Full protocol for a specific NCT (eligibility, outcomes, locations)	ClinicalTrials.gov
`get_trial_results`	Trial outcomes — endpoints, adverse events, participant flow	ClinicalTrials.gov
`get_trial_sites`	Trial site locations — facilities, countries, geo distribution	ClinicalTrials.gov
`lookup_drug`	Drug info: active ingredients, strength, ATC classification, NDC	openFDA + RxNorm
`get_approvals`	FDA approval history with submission dates and status	openFDA Drugs@FDA
`get_eu_approvals`	EU/EMA authorization — brand names, ATC, status, orphan/biosimilar flags	EMA Daily XLSX
`get_safety_data`	FAERS adverse event reports — top reactions, serious outcomes, total count	openFDA FAERS
`detect_safety_signals`	Disproportionality screening (exploratory) — AE reporting ratios	openFDA FAERS
`get_drug_label`	FDA prescribing info — indications, boxed warnings, contraindications, dosing	openFDA Drug Labeling
`get_dailymed_label`	NIH drug label (OTC + Rx) — SPL set ID, version, DailyMed URL	DailyMed (NIH/NLM)
`get_recalls`	FDA drug recalls — Class I/II/III, reasons, dates, firms	openFDA Enforcement
`get_patent_expiry`	Patent & exclusivity — approval dates, market exclusivity estimates	openFDA
`get_drug_interactions`	Drug-drug interactions — FDA label + FAERS co-reported drugs	openFDA Labeling + FAERS
`get_drug_pricing`	US drug product ID — NDC codes, manufacturers, strength, form	openFDA NDC Directory
`get_opentargets_drug`	Drug-target MOA — mechanisms, targets, clinical stage, drug type	Open Targets (EMBL-EBI)
`get_us_orphan_designations`	US FDA Orphan Drug Designations — indication, status, exclusivity	MyChem.info
`approved_for_condition`	Find drugs by indication — which are EU-approved for a condition	EMA Daily XLSX
`list_orphan_drugs`	EU orphan drug designations — filter by therapeutic area	EMA Daily XLSX
`list_biosimilars`	EU biosimilars — filter by condition / therapeutic area	EMA Daily XLSX
`list_loss_of_exclusivity`	LOE timing — biosimilar competition by active substance	EMA + FDA
`company_pipeline`	Company R&D — trials grouped by phase + EU approval enrichment	ClinicalTrials.gov + EMA
`search_publications`	PubMed search for drug/trial publications	PubMed / NCBI
`find_investigators`	KOL / PI search — investigators by condition or drug	ClinicalTrials.gov + PubMed
`detect_combination_therapies`	Combination therapy detection — co-administered drugs in trials	ClinicalTrials.gov
`compare_drugs`	Head-to-head — FDA, EU, MOA, safety, patent across 2 drugs	Composite
`drug_pipeline`	Composite — drug info + FDA + EU + safety + label + signals + recalls + interactions + trials + pubs + patent	All sources
`pipeline_landscape`	Full pipeline for a condition — approved + Phase 3/2/1 + mechanisms + sponsors + pubs	Composite

⚠️ detect_safety_signals: Exploratory disproportionality screening — uses an approximate denominator, not a validated PRR. Not for regulatory or clinical use. See methodology note in code.

Architecture

drug-pipeline-mcp/
├── drug_pipeline/
│   ├── __init__.py        # Version
│   ├── server.py          # MCP server (28 tools)
│   └── sources.py         # Data source fetchers (API aggregation layer)
├── drug_pipeline_cli.py   # CLI entry point
├── tests/                 # 61 unit tests (pytest)
├── pyproject.toml
└── README.md

Design philosophy: Lightweight API aggregation. No caching layer. No ML models. No predictions. Each tool makes real-time requests to a public API and returns structured data with source identifiers. The server is intentionally simple — it extracts, structures, and annotates, nothing more.

Limitations by design:

Rate limits apply per source (openFDA: 10 req/sec, ClinicalTrials.gov: generous)
EMA data sourced from a daily-updated XLSX register — format changes monitored manually
FAERS data is spontaneous reporting, not incidence rates
The server does not interpret, predict, or synthesize beyond what the sources provide

Data Sources

Source	Data	Access
ClinicalTrials.gov	500K+ studies, phases, status, eligibility, results, site locations	✅ Always free
openFDA NDC Directory	Drug product ID, NDC codes, manufacturers	✅ Always free
openFDA FAERS	Adverse event reports, reactions, serious outcomes	✅ Always free
openFDA Drug Labeling	Prescribing info, interactions, contraindications	✅ Always free
openFDA Drugs@FDA	Approval history, submissions, orphan designations	✅ Always free
openFDA Enforcement	Recalls, market withdrawals, safety alerts	✅ Always free
RxNorm / RxNav	Drug identifiers, RxCUI, ATC classification	✅ Always free
PubMed / NCBI	Scientific publications, abstracts, PMIDs	✅ Always free
EMA Medicines Register	EU authorization status, ATC, orphan/biosimilar flags	✅ Always free
Open Targets (EMBL-EBI)	Drug-target mechanisms of action, clinical development stage	✅ Always free
DailyMed (NIH/NLM)	Drug labels (OTC + Rx), structured product labeling	✅ Always free
MyChem.info	US FDA Orphan Drug Designations	✅ Always free

All sources are publicly funded and freely accessible. No API keys, subscriptions, or licensing required.

Verifiable Outputs

Every data point includes a direct link to its primary source:

Output Field	Example Source URL
NCT ID	`https://clinicaltrials.gov/study/NCT03178617`
FDA Application Number	`https://www.accessdata.fda.gov/scripts/cder/daf/index.cfm?event=overview.process&ApplNo=NDA125456`
PMID	`https://pubmed.ncbi.nlm.nih.gov/37272535/`
FDA Product NDC	`https://www.accessdata.fda.gov/scripts/cder/ndc/`
DailyMed SPL Set ID	`https://dailymed.nlm.nih.gov/dailymed/drugInfo.cfm?setid=xxx`

No calculated fields. No predictions. No estimates. The tool is an aggregator, not an oracle — it brings primary-source data into an AI agent's context so the LLM can apply reasoning, not so the server can produce answers.

Testing & Quality

Check	Status
Unit tests	✅ 61 passing (pytest)
CI/CD	✅ Multi-Python matrix (3.10–3.13), Docker build, PyPI publish
Linting	✅ Ruff (zero warnings)
Formatting	✅ Black-compatible
Code coverage	Tracked in CI

Regulatory Intelligence

Beyond drug-level approvals, this project provides multi-jurisdiction regulatory framework intelligence for pipeline analysis. See docs/local-regulation-2026.md for a comprehensive reference covering 7 jurisdictions:

🇺🇸 US IRA — Medicare Part D price negotiation (Sep 2026), Small Molecule Penalty (7 yr vs 13 yr)
🇩🇪 Germany AMNOG — Benefit assessment, 2026 reform with fixed effect-size thresholds
🇫🇷 France HAS/CEPS — SMR/ASMR ratings, 400–600 day access timelines
🇮🇹 Italy AIFA — 21 regional formularies, payback mechanisms
🇬🇧 UK MHRA/NICE — Post-Brexit ILAP pathway, £/QALY thresholds
🇯🇵 Japan PMDA/NHI — Sakigake designation, biennial price revision
🇨🇳 China NMPA/NRDL — Annual –61% price negotiation

Example Agent Queries

"What's in the pipeline for GLP-1 agonists?" → drug_pipeline(drug_name="semaglutide") → ATC class, FDA status, clinical trials, publications

"Which companies have Phase 3 trials for non-small cell lung cancer?" → search_trials(condition="non-small cell lung cancer", phase="PHASE3", status="RECRUITING")

"Is pembrolizumab approved in the EU vs US?" → get_approvals(drug_name="Keytruda") + get_eu_approvals(drug_name="Keytruda")

"What are the safety signals for semaglutide?" → get_safety_data(drug_name="semaglutide") + detect_safety_signals(drug_name="semaglutide")

"What does the label say for Keytruda?" → get_drug_label(drug_name="Keytruda") → indications, boxed warnings, contraindications, dosing

"When does the patent for Keytruda expire?" → get_patent_expiry(drug_name="Keytruda") → exclusivity information

"What drugs are approved for non-small cell lung cancer in the EU?" → approved_for_condition(condition="non-small cell lung cancer")

Client Integration

Claude Desktop

{
  "mcpServers": {
    "drug-pipeline": {
      "command": "python3",
      "args": ["-m", "drug_pipeline.server"]
    }
  }
}

Cursor / VS Code

{
  "mcpServers": {
    "drug-pipeline": {
      "command": "uvx",
      "args": ["drug-pipeline-mcp"]
    }
  }
}

HTTP / SSE (Remote)

pip install drug-pipeline-mcp[http]
drug-pipeline --http --port 8081

Connect at http://your-server:8081/sse.

Smithery

One-click deploy. No config needed.

🤝 Getting Help & Contributing

Channel	Purpose
💬 GitHub Discussions	Questions before coding, feature ideas, community chat
🐛 GitHub Issues	Bug reports, confirmed feature requests
📖 CONTRIBUTING.md	Development setup, code style, testing

New contributors welcome. See CONTRIBUTING.md for setup instructions.

License

MIT

This server cannot be installed

license - permissive license

quality - not tested

maintenance

How are these scores calculated?

Maintenance

–Maintainers

–Response time

2wRelease cycle

2Releases (12mo)

Commit activity

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

truthstack-mcp
Biology & Medicine Research & Data Health & Wellness
TruthStack1
A
license
A
quality
-
maintenance
Supplement safety MCP server for AI agents. FDA FAERS signals, CYP450 pathways, 584 compound aliases. Works with Claude Desktop, LangChain, CrewAI.
Last updated 2026-02-18
5
1
aria-mcp-server
Biology & Medicine Research & Data Search
pkotecha-eng
A
license
A
quality
C
maintenance
Clinical research MCP server providing real-time access to PubMed (35M+ papers) and ClinicalTrials.gov (400K+ trials). Built for trial coordinators and life sciences teams. No API key required.
Last updated 2026-07-13
3
2
MIT
BioLab MCP Server
Biology & Medicine Bioinformatics Research & Data
brahimbattou
A
license
-
quality
C
maintenance
Unified MCP server providing AI-agent-ready access to AlphaFold, PubMed, ChEMBL, Ensembl, and 37+ scientific databases.
Last updated 2026-06-08
MIT
pharma-mcp
Biology & Medicine Research & Data Open Data
pubspro
A
license
-
quality
D
maintenance
MCP server for clinical and pharmaceutical data, enabling search of ClinicalTrials.gov, PubMed, FDA, and ICH guidelines without API keys.
Last updated 2026-05-09
37
MIT

View all related MCP servers

Related MCP Connectors

Regulatory Catalysts
Regulatory Catalysts MCP — high-value biotech regulatory calendar events (keyless).
Pangolinfo Amazon Data MCP
Real-time Amazon, WIPO & PACER data for AI agents — 19 tools via the MCP protocol.
Cure Cancer With AI
Free oncology data (research, trials, FDA approvals, news) plus IBM MAMMAL biomedical predictions.

View all MCP Connectors

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/DasClown/drug-pipeline-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server