Skip to main content

​
Overview

Ambivert AI exposes an MCP (Model Context Protocol) server that lets AI assistants like Codex, Claude Code, Claude Desktop, and Cursor access your workspace and documentation. Once connected, an assistant can list your agents, fetch agent definitions, and search Ambivert AI docs on your behalf.

​
Prerequisites

  • A Ambivert AI API key. Generate one at /api-keys (or http://localhost:3010/api-keys for self-hosted). See API Keys.
  • Your Ambivert AI MCP endpoint:
    • Hosted: https://app.ambivertai.tech/api/v1/mcp/
    • Self-hosted: <YOUR_BACKEND_URL>/api/v1/mcp/
The endpoint is also shown in Platform Settings → MCP Server inside the Ambivert AI UI.
If you deployed Ambivert AI to a remote server using setup_remote.sh, your endpoint is served with a self-signed SSL certificate. Claude Code will refuse MCP connections to it unless you start the CLI with TLS verification disabled:
This is only required for self-signed certificates. If you have set up a custom domain with Let’s Encrypt certificates via Certbot, no extra flag is needed.

​
Claude Code

Register Ambivert AI as an MCP server with the Claude Code CLI:
Replace YOUR_API_KEY with the key you generated. For self-hosted deployments, swap the URL for your backend. Verify the server is connected:

​
Codex

Open Codex’s config file (~/.codex/config.toml) and add a ambivert MCP server:
Replace YOUR_API_KEY with the key you generated. For self-hosted deployments, replace the URL with your backend MCP endpoint. If you prefer to keep the API key out of config.toml, store it in an environment variable instead:
Then set the API key before starting Codex:
Verify the server is registered:

​
Claude Desktop

Open Claude Desktop’s config file (claude_desktop_config.json) and add the ambivert entry under mcpServers:
Restart Claude Desktop after saving. The Ambivert AI tools should appear in the tool picker.

​
Cursor and other MCP clients

Any MCP client that supports Streamable HTTP transport can connect with the same URL and header. Paste the configuration above into your client’s MCP settings file and replace YOUR_API_KEY.

​
Example prompts

Once the MCP server is connected, you can drive Ambivert AI from your coding agent in plain English. A few prompts to try: Explore your workspace
  • “List my agents in Ambivert AI.”
  • “Show me the definition of the agent called Lead Qualifier.”
  • “Which credentials and tools are configured in my Ambivert AI workspace?”
  • “List the recordings from my most recent agent.”
Edit an agent
  • “In my Lead Qualifier agent, add a new agent node after the greeting that asks the caller for their budget, then routes to the existing qualification node.”
  • “Add an end-call node to Support Bot that triggers when the user says they are done, with a polite goodbye prompt.”
  • “Rename the intro node in Lead Qualifier to greeting and update any edges that reference it.”
  • “Change the LLM model on all agent nodes in Support Bot to gpt-4o-mini.”
Learn the platform
  • “Search the Ambivert AI docs for how to configure a TURN server.”
  • “What node types does Ambivert AI support, and what fields does a knowledge_base node take?”
  • “How do I deploy Ambivert AI on a custom domain with HTTPS?”
Agent edits are saved as a new draft version — your published agent keeps serving calls until you explicitly publish the draft from the Ambivert AI UI.
The API key controls which workspace the assistant sees. Treat it like any other credential — do not commit it to source control or paste it into shared chats.