Real World Evidence

Disclaimer– All data is synthetically generated for demonstration purposes only. Donotuse for clinical or regulatory decisions.

cd rwe_mcp_server pip install -r requirements.txt

The server starts onStreamable HTTPat:

- MCP endpoint:http://127.0.0.1:9090/mcp
- Health endpoint:http://127.0.0.1:9090/health

You can override the bind address, port, or transport:

MCP_HOST=0.0.0.0 MCP_PORT=9090 python server.py MCP_TRANSPORT=stdio python server.py

Open (or create)claude_desktop_config.json:

Add the server entry below (replace/absolute/path/to/with your actual path):

{ "mcpServers": { "rwe-life-sciences": { "command": "python", "args": ["/absolute/path/to/rwe_mcp_server/server.py"], "env": { "MCP_TRANSPORT": "stdio" } } } }

If you use a virtual-environment interpreter:

{ "mcpServers": { "rwe-life-sciences": { "command": "/absolute/path/to/.venv/bin/python", "args": ["/absolute/path/to/rwe_mcp_server/server.py"], "env": { "MCP_TRANSPORT": "stdio" } } } }

Restart Claude Desktop. The 🔧 tool icon should showrwe-life-sciencesconnected.

- Type 2 Diabetes
- Hypertension
- Heart Failure
- COPD
- Asthma
- Atrial Fibrillation
- Major Depressive Disorder
- Rheumatoid Arthritis
- Chronic Kidney Disease
- Obesity

Show me the real-world evidence for Type 2 Diabetes across all dimensions. What is the geographic distribution of Heart Failure patients in the Northeast between 2020 and 2024? Compare the longitudinal trend for COPD from 2018 to 2024. Break down Hypertension prevalence by age and gender only.

{ "metadata": { ... }, // source, condition, ICD-10 codes, caveats "summary": { ... }, // total cohort KPIs "by_age": [ ... ], // one row per age group "by_gender": [ ... ], // one row per gender "by_geography": [ ... ], // regions → states "longitudinal": [ ... ] // one row per year }

rwe_mcp_server/ ├── server.py # MCP server + tool implementation ├── requirements.txt # Python dependencies (mcp) └── README.md # This file

Bioinformatics data for AI agents — gene search, protein structures, clinical variants, PubMed literature, and DNA sequences via NCBI and UniProt. No API key required.

Pharmacovigilance intelligence — 165 tools for drug safety data (FDA FAERS, EudraVigilance, WHO, PubMed, ClinicalTrials.gov), signal detection (PRR/ROR/IC/EBGM), causality assessment, and guided research courses. Open, no auth required.

Interact with Omics AI Explorer networks for genomics research and data analysis.

Search NHTSA vehicle recalls and FDA food/drug recalls in real-time. 4 MCP tools for product safet monitoring.

A nutrition analysis platform integrating Canada's Food Guide recipes with Health Canada's official nutrition databases.

Search and access clinical trial data from ClinicalTrials.gov.

Free oncology data (research, clinical trials, FDA approvals, news) plus IBM MAMMAL biomedical predictions, exposed as MCP tools.

Edama remote MCP effectively gives an AI the ability to "understand" food in the same way a nutritionist would, by translating natural language descriptions, images or barcodes into structured nutrition and food.

An AI-powered API for medical research, unifying ClinicalTrials.gov, PubMed, and FDA databases with intelligent analysis.

A server for searching, retrieving, and analyzing articles from the PubMed database.