AssemblyAI MCP server
AssemblyAI's official server lets coding agents search and read its speech-to-text and audio-intelligence documentation on demand.
AssemblyAI MCP is the official documentation server from AssemblyAI, the speech-to-text and audio-intelligence provider. It exists so that an AI coding agent can look up the right way to call AssemblyAI's APIs while it writes integration code, instead of guessing parameters from stale training data. The agent can search across every guide, API reference page, tutorial, FAQ, and cookbook, browse the documentation structure section by section, fetch the full markdown of one or more pages in a single call, and pull endpoint-level details — request and response schemas, parameters, and descriptions — for the REST API, the Universal-Streaming WebSocket API, and the LLM Gateway.
The server runs at https://mcp.assemblyai.com/docs over Streamable HTTP and requires no authentication, so any MCP-capable client can connect with a single add command. It is a documentation-grounding server: it does not transcribe audio itself, but it keeps an agent's AssemblyAI integration code accurate as the APIs evolve.
Quick install
Copy-paste configs are provided for all 8 supported clients. Pick your client below.
Add to ~/.claude.json
{
"mcpServers": {
"assemblyai": {
"type": "http",
"url": "https://mcp.assemblyai.com/docs"
}
}
}claude mcp add --transport http assemblyai https://mcp.assemblyai.com/docsAvailable tools
| Tool | Description |
|---|---|
| search_docs | Searches across all AssemblyAI documentation — guides, API reference, tutorials, FAQ, and cookbooks — returning matching pages with relevant excerpts. |
| get_pages | Retrieves the full markdown content of one or more AssemblyAI documentation pages by path, supporting multiple pages in a single call to reduce round-trips. |
| list_sections | Lists all sections and pages in the AssemblyAI documentation, useful for understanding the structure and finding the right topic. |
| get_api_reference | Gets details about AssemblyAI API endpoints — request/response schemas, parameters, and descriptions — covering the REST API, Streaming WebSocket API, and LLM Gateway. |
What you can do with it
Accurate integration code
While building a transcription feature, the agent searches the docs and reads the exact request and response schema for an endpoint instead of inventing parameters.
Mid-task documentation lookups
As the agent iterates on a feature it pulls several pages at once with get_pages, keeping the AssemblyAI API usage current without leaving the session.
FAQ
- Is it free?
- Yes. The documentation MCP server is free and requires no authentication; you only pay for AssemblyAI usage when you call the actual transcription APIs from your own code.
- Does it support remote/OAuth?
- It is a hosted remote endpoint at https://mcp.assemblyai.com/docs over Streamable HTTP with no authentication required, so no OAuth or API key is needed to connect.