Get started
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#
claude mcp add --transport http tts-cache-router-docs https://docs.ttscacherouter.dev/mcpThis adds it to the project you run it in. Add --scope user to have it in every project.
Codex#
codex mcp add tts-cache-router-docs --url https://docs.ttscacherouter.dev/mcpThis adds it to every project.
Cursor#
Add it to .cursor/mcp.json in your project, or to ~/.cursor/mcp.json for every project:
{ "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_docsquery, limit- Searches every page and returns the best-matching sections, with each one's page and link.
get_doc_pagepath- 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. llms.txt lists every page, and llms-full.txt holds them all in one file.