Aymar Agents has its own MCP server (Model Context Protocol): it exposes your account — leads, contacts, conversations, appointments and tickets — as a set of tools your AI assistant can read and, with your confirmation, write to. It’s exactly what the public API allows, not one endpoint more — its tools are generated from the same OpenAPI definition.
What it is and what it is notA deterministic adapter over your own public API, with no language model of its own.
Connect your assistantURL, X-Api-Key header and Streamable HTTP transport.
Connect your client
Section titled “Connect your client”Claude DesktopDesktop client configuration.
Claude CodeVia CLI or with .mcp.json.
CursorEditor configuration.
Reference
Section titled “Reference”Tool catalogEvery available tool, generated from the same OpenAPI definition as the public API.
Confirmation on writesNo write happens without your explicit confirmation.
Limits, errors and troubleshootingWhat to do when something fails.
Related tools
Section titled “Related tools”API referenceThe same surface, in plain REST.
llms.txtAn index of the whole portal in plain text.
Frequently asked questions
Section titled “Frequently asked questions”How is the own MCP server different from an external MCP server (BYO-MCP)?
They run in opposite directions: Aymar Agents's MCP server exposes your account to your external AI assistant (Claude Desktop, Claude Code, Cursor); an external MCP server plugs third-party tools into the agent that talks to your own customers, and it's connected from Settings, not from your MCP client. See What it is and what it is not.
What do I need to connect my MCP client?
A Pro or Enterprise plan and an API key with the scopes of the resources you want to use — the same mechanism you'd use to call /public/v1 directly.
Can the MCP server do more than the public API?
No — its tools are generated by reading the exact same OpenAPI definition as /public/v1. Anything you can do through MCP you could also do with a direct curl call to the API.
Why does my assistant ask for confirmation before creating or changing something?
Every write tool requires the confirm: true argument; without it, the server rejects the call before touching the API and returns a summary of what it was about to do. It's the same "the LLM is never the only barrier" principle that governs the rest of the product. See Confirmation on writes.
Can an MCP tool delete data?
No — no tool can delete anything, because the public API has no DELETE endpoint at all.
I only see the status tool in my MCP client, nothing else. Why?
Either your tenant isn't on a Pro/Enterprise plan, or your key has no read scope at all. Call the status tool to confirm which one it is. See Limits, errors and troubleshooting.
Up next
Section titled “Up next”Connect your assistantConfiguration blocks for Claude Desktop, Claude Code and Cursor.