You need a server key — create one in Settings → API keys. The same page
shows these snippets ready to copy, under Connect an AI assistant.
Pick what the assistant may do
The key’s access decides which tools your assistant even sees:
Start with Build. Create a separate full-access key only when you want the
assistant to send or call, and revoke it when you are done.
The key can message your customers and place calls. Keep it in your
assistant’s config on your own machine — never in a repository, a shared
document or a web page. If it leaks, revoke it in Settings → API keys;
that takes effect immediately.
Run in a terminal:Check it with claude mcp list, or /mcp inside a session. Add to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (one project): Clients that only run local servers connect through mcp-remote, which
needs Node.js. In Claude Desktop: Settings →
Developer → Edit config:The key is passed through env deliberately: some clients split arguments
on spaces, which breaks Bearer ta_live_… written inline.
Check it works
Ask your assistant: “List my ThinnestAI agents.” It should call
list_agents and show them.
If it does not connect