openevidence-mcp

MCP.Pizza Chef: bakhtiersizhaev

This server connects your AI assistant to your own OpenEvidence browser session, letting you search, retrieve, and ask medical research questions using your authenticated account. It works with popular MCP clients like Claude Desktop, Cursor, and VS Code without needing an API key. You set it up by pasting a config snippet and logging into OpenEvidence via a local browser session. It helps clinicians and researchers integrate evidence-based info into their AI workflows securely and locally.

Other
Web/Research

Use This MCP server To

Search my OpenEvidence question and article history Fetch full medical research articles by ID Ask new medical research questions to OpenEvidence Check if my OpenEvidence session is logged in Wait for research articles to complete processing Integrate OpenEvidence research into my AI assistant workflows

README

OpenEvidence MCP (Unofficial)

OpenEvidence MCP is an unofficial Model Context Protocol server that connects OpenEvidence to Codex, Claude Code, Claude Desktop, Cursor, Cline, Continue, and other MCP-compatible clients through your own authenticated browser session.

License: Apache-2.0 Node.js 20+ TypeScript MCP SDK Playwright

Important

This project is unofficial and is not affiliated with OpenEvidence. It does not provide medical advice, does not bypass access controls, and should only be used with your own OpenEvidence account in compliance with applicable terms, privacy rules, and clinical governance requirements.

Translations: Русский | Español | 简体中文 | 繁體中文(台灣) | 한국어 | हिन्दी

Agent Onboarding & Installation

Using Codex, Claude Code, Cursor, or another local AI coding agent? You can let the agent handle the entire setup, compilation, and local MCP configuration for you!

Copy and paste this short bootstrap prompt directly into your local AI coding assistant:

Please install OpenEvidence MCP for me: clone https://github.com/bakhtiersizhaev/openevidence-mcp, install dependencies, run build, auto-configure this MCP server in my local client (Claude Desktop/Codex/Cursor), guide me through the one-time Edge/Chrome login using `npm run login:session`, and run `npm run smoke` to verify. Keep everything strictly local and secure.

For the comprehensive, step-by-step setup playbook and rules, see docs/AGENT_INSTALL_PROMPT.md.

openevidence-mcp FAQ

Can I use this to search and retrieve medical research articles from OpenEvidence?
Yes — it lets your AI access your OpenEvidence browser session to find and fetch articles you have access to.
Can I use this with Claude Desktop or VS Code?
Yes — it works with Claude Desktop, Cursor, VS Code, Cline, and other MCP-compatible clients.
Do I need an OpenEvidence account to use this?
Yes — you must log in to your own OpenEvidence account through the local browser session for access.
Is an API key required?
No — it uses your authenticated browser session, so no separate API key is needed.
How hard is it to set up?
Setup is copy-paste-config level — you paste a small config snippet and follow guided login steps.
Does it provide medical advice or bypass paywalls?
No — it only accesses your authorized session and does not give medical advice or bypass controls.
What platforms does it support?
It runs on macOS, Windows, and Linux with Node.js 20+ and Chromium installed via Playwright.