EmDash Docs MCP

The EmDash documentation site exposes a public Model Context Protocol server at https://docs.emdashcms.com/mcp. Connect a coding assistant to search the published docs while you work.

This is separate from your site’s MCP server (covered in the AI Tools guide). The docs MCP only knows about EmDash’s documentation — it cannot read or modify your content. Connect the docs MCP for documentation lookup, the site MCP for content management, or both when the assistant needs both kinds of access.

What it does

The docs MCP exposes a single tool:

Tool	Purpose
`search_docs`	Search the EmDash documentation. Returns relevant chunks with source URLs and match scores.

The server uses Cloudflare AI Search over an index of docs.emdashcms.com. Results contain source URLs and matching passages; the AI client decides how to use them in its answer.

Connect it

The server is reachable at the following endpoint, with no authentication or API key. It is public and read-only.

https://docs.emdashcms.com/mcp

Auto-discovery in EmDash templates

If you started your project from an EmDash template (npm create emdash), three config files are already in place and will be picked up automatically:

File	Used by
`.mcp.json`	Claude Code
`.cursor/mcp.json`	Cursor
`.vscode/mcp.json`	VS Code

Open the project and accept the workspace-trust prompt the tool shows on first run. No further setup is required.

Manual setup

If you’re not using a template, or you use a different tool, add it once with the snippet for your client:

Codex

Add the public remote server with the Codex CLI:

codex mcp add emdash-docs --url https://docs.emdashcms.com/mcp

The ChatGPT desktop app, Codex CLI, and IDE extension share MCP configuration for the same Codex host. The official Codex MCP documentation covers the CLI, config.toml, and current transport support.

ChatGPT

ChatGPT developer mode can create an app from a remote MCP server with no authentication. Use the docs MCP endpoint when creating the app. Follow the official ChatGPT developer mode guide for current eligibility and controls instead of relying on a copied settings path.

Claude Code

The following command adds the server with the Claude Code CLI:

claude mcp add --transport http emdash-docs https://docs.emdashcms.com/mcp

Alternatively, commit the same .mcp.json file that EmDash templates provide:

{
  "mcpServers": {
    "emdash-docs": {
      "type": "http",
      "url": "https://docs.emdashcms.com/mcp"
    }
  }
}

OpenCode

Add the following entry to opencode.jsonc:

{
  "mcp": {
    "emdash-docs": {
      "type": "remote",
      "url": "https://docs.emdashcms.com/mcp"
    }
  }
}

Cursor

Commit a .cursor/mcp.json file at the project root with the following contents. For user-level or interface setup, follow Cursor’s MCP documentation:

{
  "mcpServers": {
    "emdash-docs": {
      "type": "http",
      "url": "https://docs.emdashcms.com/mcp"
    }
  }
}

VS Code

Add the following entry to .vscode/mcp.json in the project. For user-level configuration and trust controls, follow Visual Studio Code’s MCP documentation:

{
  "servers": {
    "emdash-docs": {
      "type": "http",
      "url": "https://docs.emdashcms.com/mcp"
    }
  }
}

Claude

Add the endpoint as a remote custom connector. Connector screens and plan requirements are controlled by Anthropic, so follow its current remote MCP connector instructions.

When to use it

You’re building an EmDash site and want your AI assistant to look up the correct API, hook name, or config option from current docs rather than half-remembered training data.
You’re writing a plugin and want to find which hooks fire in what order.
You’re porting a WordPress theme and want examples of seed file patterns.
You’re stuck on an error and want to search release notes and concepts.

Recommend it in `AGENTS.md`

If your project uses AGENTS.md (or CLAUDE.md, .cursorrules, etc.) to instruct AI tools, point them at the docs MCP so they prefer real documentation over assumptions:

## Documentation

Look up EmDash documentation via the `emdash-docs` MCP server when you need to
verify an API, hook, config option, or pattern. Prefer the docs MCP over
assumptions from training data -- the docs reflect the current published
behaviour.

The EmDash starter templates ship with this snippet pre-included.