# AI coding tools

> Let Claude Code, Codex, Cursor or another coding agent search and read these docs, through the docs' MCP server or as Markdown.

## The docs MCP server

Add the docs to your coding agent, and it can search and read them while it connects your agent to the router.

The server is at `https://docs.ttscacherouter.dev/mcp`, over Streamable HTTP. It is public and needs no key.

### Claude Code

```shell
claude mcp add --transport http tts-cache-router-docs https://docs.ttscacherouter.dev/mcp
```

This adds it to the project you run it in. Add `--scope user` to have it in every project.

### Codex

```shell
codex mcp add tts-cache-router-docs --url https://docs.ttscacherouter.dev/mcp
```

This adds it to every project.

### Cursor

Add it to `.cursor/mcp.json` in your project, or to `~/.cursor/mcp.json` for every project:

**.cursor/mcp.json**

```json
{
  "mcpServers": {
    "tts-cache-router-docs": {
      "url": "https://docs.ttscacherouter.dev/mcp"
    }
  }
}
```

### Other clients

Any MCP client that connects to a server by URL can use it: give it `https://docs.ttscacherouter.dev/mcp` as a Streamable HTTP (sometimes called HTTP) server.

## Its tools

- `search_docs` (`query, limit`): Searches every page and returns the best-matching sections, with each one's page and link.
- `get_doc_page` (`path`): One page as Markdown, with its code samples, by path (`/livekit/elevenlabs`) or URL.
- `list_doc_pages`: Every page, with its path and what it covers.

## The docs as Markdown

Without MCP, an agent can read the docs as Markdown: every page has a copy at its URL plus `.md`, like [`https://docs.ttscacherouter.dev/quickstart.md`](https://docs.ttscacherouter.dev/quickstart.md). [llms.txt](https://docs.ttscacherouter.dev/llms.txt) lists every page, and [llms-full.txt](https://docs.ttscacherouter.dev/llms-full.txt) holds them all in one file.