How do I install the openevidence mcp server?

Use a recorded configuration for your client, replace example credential values and paths, and verify the documented runtime. Restart or reconnect the client, then inspect the available tools.

SSyncDev

Start a project

Openevidence MCP Server

Unofficial MCP server connecting OpenEvidence to AI agents via authenticated browser sessions

Local serverstdio

What is the Openevidence MCP Server?

Unofficial MCP server connecting OpenEvidence to AI agents via authenticated browser sessions

What you get

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.

checking whether the saved session is authenticated;
listing your OpenEvidence question/article history;
fetching a full article payload by ID;
asking an OpenEvidence research question and optionally waiting for completion;
polling an existing OpenEvidence article until it completes

Configuration and credentials

Node.js 20+ - npm 10+ - OpenEvidence account - macOS, Windows, or Linux - Chromium installed by Playwright (npx playwright install chromium)

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

Tool	What it does
authenticated	true
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.

How to install the Openevidence MCP Server

{
  "mcpServers": {
    "openevidence": {
      "command": "node",
      "args": ["/ABSOLUTE/PATH/openevidence-mcp/dist/server.js"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

Node.js 20+ - npm 10+ - OpenEvidence account - macOS, Windows, or Linux - Chromium installed by Playwright (npx playwright install chromium)

Example prompts to try

“Use Openevidence to Windows.”
“Use Openevidence to authenticated.”
“Use Openevidence to Client.”

Frequently asked questions

Unofficial MCP server connecting OpenEvidence to AI agents via authenticated browser sessions Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.

Alternatives to the Openevidence MCP Server

Playwright

Official

Use Microsoft’s Playwright MCP server to navigate pages, inspect accessibility snapshots, fill forms and capture browser screenshots.

Browser AutomationTypeScript★ 21.0k

Puppeteer

Official

The original Chromium automation reference server — simple, screenshot-driven browser control.

Browser AutomationTypeScript★ 63.0k

Datapoint MCP

LLMs are great at generating options and bad at telling you which one a real person will prefer. Datapoint MCP closes that loop — your agent can hand

Productivity & Project ManagementGo

Can

Let AI agents see and interact with terminal/CLI apps via PNG screenshots

Browser Automation

TurnSignal

Read-only Playwright CI results for agents: new vs known failures, flaky tests, test history.