Connect the docs MCP server

These docs ship with a Model Context Protocol (MCP) server at https://docs.speechify.ai/_mcp/server. Connect it to your AI coding tool to ask grounded questions about the Speechify API, SDKs, and docs, with citations to the page each answer came from, without leaving your editor.

What you get

One-click install

The actions menu at the top of every docs page carries Connect to Claude Code (copies the claude mcp add command) and Connect to Cursor (installs the server through a deep link). For any other client, or to configure one by hand, use the sections below.

Claude Code

claude mcp add --transport http speechify-docs https://docs.speechify.ai/_mcp/server

Cursor

Add the server to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "speechify-docs": {
      "type": "http",
      "url": "https://docs.speechify.ai/_mcp/server"
    }
  }
}

VS Code

Add the server to your VS Code mcp.json (used by Copilot):

{
  "servers": {
    "speechify-docs": {
      "type": "http",
      "url": "https://docs.speechify.ai/_mcp/server"
    }
  }
}

Windsurf

Add the server to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "speechify-docs": {
      "type": "http",
      "url": "https://docs.speechify.ai/_mcp/server"
    }
  }
}

Claude Desktop

Add the server to your Claude Desktop config (claude_desktop_config.json):

{
  "mcpServers": {
    "speechify-docs": {
      "type": "http",
      "url": "https://docs.speechify.ai/_mcp/server"
    }
  }
}

Config file locations:

No MCP client

An agent that can fetch a URL does not need MCP to read these docs. Append .md to any page URL for clean Markdown, and start from https://docs.speechify.ai/llms.txt for the full page index.

Verify the connection

Restart your client, then ask it something only the docs would know, for example:

How do I stream text-to-speech audio with the Speechify API?

The client should call the searchDocs tool and answer with citations to the Speechify docs.