OpenEvidence MCP

Name: OpenEvidence MCP
Author: bakhtiersizhaev

@bakhtiersizhaev

关于 OpenEvidence MCP

Open-source MCP server that connects OpenEvidence clinical evidence workflows to AI clients using browser-session auth (Playwright), no API key required.

#medical-research #evidence-based-medicine #clinical-decision-support #healthcare-ai #mcp-server #playwright

基本信息

分类

浏览器自动化

传输方式

stdio

发布者

bakhtiersizhaev

提交者

Bakhtier Sizhaev

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "openevidence": {
      "command": "npx",
      "args": [
        "-y",
        "openevidence-mcp"
      ]
    }
  }
}

工具

validate account session (`/api/auth/me`)

list conversation history (`/api/article/list`)

fetch full article payload by ID

ask a question and optionally wait for completion

概览

What is OpenEvidence MCP?

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.

How to use OpenEvidence MCP?

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.

Key features of OpenEvidence MCP

Bridges OpenEvidence to popular MCP clients
Uses your own browser session via Playwright storage state
Offers four tools: auth check, history list, article fetch, ask
Supports macOS, Windows, and Linux
No public API token required
Open source under Apache‑2.0

Use cases of OpenEvidence MCP

Query clinical evidence while coding in Claude Desktop
Fetch full article payloads by ID from Cursor
List conversation history to review past questions
Check account session validity before running workflows
Automate clinical evidence retrieval in Cline or Codex CLI

FAQ from OpenEvidence MCP

What is OpenEvidence MCP and why was it created?

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.

What tools does OpenEvidence MCP provide?

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).

What platforms are supported?

macOS, Windows, and Linux are supported.

How does authentication work?

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.

Is this an official integration?

No, it is an unofficial server. The official OpenEvidence platform does not provide a public API token flow for third‑party MCP integrations.

浏览器自动化分类下的更多 MCP 服务器

Playwright Mcp

microsoft

Playwright MCP server

34.8K

Webpage Screenshot MCP Server

ananddtyagi

An MCP that gives your agent the ability to snap a screenshot of webpages. Useful when you want your agent to check its progress during development.

Fastcrw

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.

286

Browserbase MCP Server

browserbase

Allow LLMs to control a browser with Browserbase and Stagehand

3.4K

Slack Slack