@bakhtiersizhaev
Basic information
Open-source MCP server that connects OpenEvidence clinical evidence workflows to AI clients using browser-session auth (Playwright), no API key required.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"openevidence": {
"command": "npx",
"args": [
"-y",
"openevidence-mcp"
]
}
}
}Check whether the saved OpenEvidence browser session is authenticated. Use before history/article/ask tools when auth state is unknown. Returns authenticated=true/false and basic account metadata when available. Requires the local browser profile created by npm run login:session. No side effects. Can fail if the profile is missing, expired, or network access fails.
List prior OpenEvidence articles from the authenticated account. Use only when the user asks to inspect prior OpenEvidence work or needs an article_id. Inputs: limit, offset, optional search, optional include_raw=false. Returns a privacy-reduced list by default; include_raw=true may expose private prior questions and must be used only with explicit user intent. Requires authenticated session. No side effects.
Fetch an OpenEvidence article by article_id. Use after history lookup or oe_ask returns an article ID. Inputs: article_id UUID, optional include_raw=false. Returns normalized status, question, and answer fields by default. include_raw=true may expose private thread context and must be used only with explicit user intent. Requires authenticated session. No side effects.
Wait for an existing OpenEvidence article_id to finish, then return normalized fields. Use after oe_ask with wait_for_completion=false, especially for long research questions that may exceed MCP host timeouts. Inputs: article_id UUID, optional timeout_sec, poll_interval_ms, and include_raw=false. include_raw=true may expose private thread context and must be used only with explicit user intent. Requires authenticated session. No side effects.
Create an OpenEvidence research question, not medical advice or patient-specific diagnosis. For long questions, prefer wait_for_completion=false and then call oe_article_wait with the returned article_id. Use original_article_id only for true follow-up continuity; omit it for fresh questions. Returns privacy-reduced created article data and optionally normalized completed fields. Side effect: creates a question/article in the user's OpenEvidence account through the local browser profile.
OpenEvidence MCP is an unofficial Model Context Protocol server that bridges OpenEvidence to MCP clients (Codex CLI, Claude Desktop/Code, Cursor, Cline, Continue). It uses your own browser session via Playwright storage state to enable clinical evidence workflows from AI assistants, since OpenEvidence lacks a public API token flow.
Provide a captured Playwright storage state from your authenticated OpenEvidence browser session, then configure your MCP client to invoke the server. Use the provided tools (oe_auth_status, oe_history_list, oe_article_get, oe_ask) in your AI coding assistant.
It is an unofficial MCP server that bridges OpenEvidence to MCP clients. It was created because OpenEvidence has no public API token flow for third‑party integrations, so it uses your own browser session instead.
It provides four tools: `oe_auth_status` (validate account session), `oe_history_list` (list conversation history), `oe_article_get` (fetch full article by ID), and `oe_ask` (ask a question with optional completion wait).
macOS, Windows, and Linux are supported.
Authentication is handled by your own browser session captured as a Playwright storage state. No API token is needed; the server uses your existing OpenEvidence login.
No, it is an unofficial server. The official OpenEvidence platform does not provide a public API token flow for third‑party MCP integrations.
An MCP server for generating images from HTML & CSS or screenshots of URLs using htmlcsstoimage.com.
🔮 Platform-neutral Browser Use for AI agents: real Chrome automation with a CLI + SDKs, no lock-in, dead simple.
Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary.
Allow LLMs to control a browser with Browserbase and Stagehand
Monitor browser logs directly from Cursor and other MCP compatible IDEs.
Comments