Unofficial MCP server connecting OpenEvidence to AI agents via authenticated browser sessions
Openevidence MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Unofficial MCP server connecting OpenEvidence to AI agents via authenticated browser sessions.
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.
Installation goes through your MCP client rather than a global install: point it at playwright on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Once Openevidence is connected, these are the calls the assistant has available:
Windows — %USERPROFILE%.openevidence-mcp\browser-profileauthenticated — trueClient — StatusCursor — CompatibleCline — CompatibleContinue — Compatibleoe_auth_status — Checks whether the saved OpenEvidence browser session is authenticatedoe_history_list — Lists prior OpenEvidence articles with optional pagination and search. Returns a privacy-reduced list unless include_raw=true is explicitly requestedoe_article_get — Fetches an article by ID and returns normalized fields (status, is_complete, question, answer_text). Raw payload is opt-in with include_raw=trueoe_article_wait — Waits for an existing article ID to complete; useful after non-blocking oe_askoe_ask — Creates an OpenEvidence research question and optionally waits for the article to completemacOS — The macOS tool exposed by this servernpx playwright install chromium)This sits in the browser automation group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Openevidence's toolset — Windows, authenticated, Client and 10 more — is a fair guide to whether it matches your workflow. It is maintained by bakhtiersizhaev; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Openevidence's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Windows | %USERPROFILE%\.openevidence-mcp\browser-profile |
| authenticated | true |
| Client | Status |
| Cursor | Compatible |
| Cline | Compatible |
| Continue | Compatible |
| oe_auth_status | Checks whether the saved OpenEvidence browser session is authenticated. |
| oe_history_list | Lists prior OpenEvidence articles with optional pagination and search. Returns a privacy-reduced list unless include_raw=true is explicitly requested. |
| oe_article_get | Fetches an article by ID and returns normalized fields (status, is_complete, question, answer_text). Raw payload is opt-in with include_raw=true. |
| oe_article_wait | Waits for an existing article ID to complete; useful after non-blocking oe_ask. |
| oe_ask | Creates an OpenEvidence research question and optionally waits for the article to complete. |
| macOS | The macOS tool exposed by this server. |
| Codex | The Codex tool exposed by this server. |
{
"mcpServers": {
"openevidence": {
"command": "node",
"args": ["/ABSOLUTE/PATH/openevidence-mcp/dist/server.js"]
}
}
}Configuration as documented by the project. Restart the client after saving.
npx playwright install chromium)Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.