Docs MCP

This is a developer MCP — it searches the documentation and explains the Evidence markdown syntax. It does not connect to your data. To query your own Evidence instance, use the Studio MCP instead.

The Evidence Docs MCP server lets AI assistants search and read the Evidence documentation. It’s available at https://evidence.studio/mcp and uses Streamable HTTP.

Built-in to Evidence Editor

The Docs MCP server is integrated into the Evidence Editor AI chat by default. When you use the AI assistant in the Evidence Editor, it automatically has access to all Evidence documentation and component information—no additional configuration needed.

Adding to Other AI Tools

You can add the Evidence Docs MCP server to other AI tools that support MCP:

Claude Code
Cursor
ChatGPT
Claude.ai

claude mcp add --transport http evidence-studio https://evidence.studio/mcp

Add the following to your Cursor MCP configuration (.cursor/mcp.json):

{
  "mcpServers": {
    "evidence-studio": {
      "url": "https://evidence.studio/mcp"
    }
  }
}

ChatGPT requires enabling Developer Mode to use MCP servers:

Go to Settings → ChatGPT Security
Scroll to find Developer Mode, and toggle it on.
Navigate to ChatGPT Plugins in the sidebar, then click the New Plugin button +

(Optional) Add an image (e.g., the Evidence logo)
Enter a name (“Evidence Docs”)
Enter a description (“Search the Evidence documentation and component reference”)
Enter the Remote MCP server URL: https://evidence.studio/mcp
Set Auth to No Auth

Click “I accept and want to continue” then Create

The Evidence documentation tools will now be available in your ChatGPT conversations.

Go to Claude.ai Settings → Connectors
Click Add Custom Connector
Enter a name (e.g., “Evidence Docs”)
Paste the Remote MCP server URL: https://evidence.studio/mcp
Click Add to save

The Evidence documentation tools will now be available in your Claude.ai conversations.

Available Tools

The Docs MCP server provides the following tools for AI assistants:

Tool	Description
`list_components`	Get the full list of Evidence components organized by category
`get_component`	Get metadata for a component including name, description, category, example, and attributes summary
`get_component_attributes`	Get detailed attribute information for a component (type, required, default, description)
`get_component_examples`	Get all code examples for a specific component
`list_docs`	List all documentation pages with titles and paths, optionally filtered by category
`read_doc`	Get the full content of a documentation page
`search_docs`	Search across all Evidence documentation

LLM-Friendly Documentation

For AI tools that don’t support MCP, the Evidence documentation is also available in plain text formats:

docs.evidence.studio/llms.txt - Sitemap of all documentation pages
docs.evidence.studio/llms-full.txt - Full documentation in a single markdown file

Get Started

Core Concepts

Features

MCP

CLI

Warehouses

Evidence Warehouse

Components

Built-in to Evidence Editor

Adding to Other AI Tools

Available Tools

LLM-Friendly Documentation

​Built-in to Evidence Editor

​Adding to Other AI Tools

​Available Tools

​LLM-Friendly Documentation

Built-in to Evidence Editor

Adding to Other AI Tools

Available Tools

LLM-Friendly Documentation