Wirestack
AssemblyAI launches an MCP server to transcribe and analyze audio from Claude, Cursor and VS Code (November 3, 2026)
Add mcp.assemblyai.com/mcp to your MCP client: five tools to submit, read, summarize and analyze transcripts at normal API rates.
Your keys
0 of 1 ready
Create each key on its own page, paste it below, then copy the finished lines into your project's .env file. What you paste stays in this tab. It is never sent to Wirestack or saved.
- AssemblyAI API keyASSEMBLYAI_API_KEYGet key
Your key is on the dashboard, or in the sidebar under Workspace, Manage, API Keys
What changed
On November 3, 2026 AssemblyAI launched an official MCP server. It lets Claude, Cursor, VS Code and other MCP clients transcribe, summarize and analyze audio on your AssemblyAI account.
- Server address:
https://mcp.assemblyai.com/mcp - Sign in with your AssemblyAI account, or send your API key as
Authorization: Bearer YOUR_API_KEY. - Five tools:
submit_transcript,get_transcript,summarize_transcript,understand_transcriptanddelete_transcript. - Usage is billed at your normal API rates.
- It is in the official MCP Registry as
com.assemblyai/mcp.
This is not the docs MCP server at https://www.assemblyai.com/docs/mcp, which only helps coding agents read the docs.
Prerequisites
- An AssemblyAI account, or an AssemblyAI API key in
ASSEMBLYAI_API_KEY - An MCP client such as Claude, Cursor or VS Code
Steps
- Add
https://mcp.assemblyai.com/mcpas a remote MCP server in your client. - Sign in with your AssemblyAI account when the client asks, or set the
Authorizationheader toBearerfollowed by your API key.
Test it
Ask your client to "transcribe this call and list the action items" with a link to an audio file. It should call submit_transcript, then get_transcript, and reply with the transcript and the action items.
Not confirmed
- Client-specific setup steps are on the MCP server docs page, not in the changelog.