An unofficial local stdio MCP server that lets MCP-compatible clients use an authenticated OpenEvidence browser session. It can check auth status, list history, fetch articles, ask research questions, and wait for article completion without requiring an OpenEvidence API token.
From the registry: Unofficial MCP server connecting OpenEvidence to AI agents via authenticated browser sessions
$ npx playwright install chromiumhttps://playwright.dev/$ npm run build$ npm run login:sessionhttps://www.openevidence.com/Please install the `openevidence-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Node.js 20+ and npm 10+** — Node.js 20 or newer is required; npm 10 or newer is also required. (https://nodejs.org/)
- **Install Playwright Chromium browser** — Chromium must be installed via Playwright for the server to function. Run: `npx playwright install chromium` (https://playwright.dev/)
- **Build the server locally** — The README requires building the project before registering the MCP server. Run: `npm run build`
- **Authenticate your OpenEvidence browser session** — Run the one-time session login flow and sign in with your own OpenEvidence account using the local browser profile. Run: `npm run login:session` (https://www.openevidence.com/)
Canonical MCP server config (stdio transport):
- command: `node`
- args: ["<absolute-path-to-openevidence-mcp>/dist/server.js"]
Note: Preferred install path in the README is local clone/build/manual registration (or the provided auto-installer), not an npx stdio launch command. The server runs locally over stdio and reuses a local browser profile for authentication. Use an absolute path to dist/server.js.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.MCP server for Firecrawl web scraping, structured data extraction and web search integration.