maxclicks MCP Server

Work with your maxclicks workspace from an MCP-compatible assistant. Ask it to inspect an audience, update a customer record, or use a template your team has prepared. The assistant calls the API with the permissions of the key you connect.

This works through the Model Context Protocol, which is how assistants pick up tools. The server supports remote streamable HTTP and local stdio. The configuration below uses the documented hosted address; verify that your environment can reach it before relying on it. Remote clients authenticate with an API key.

Current API coverage

The documented tool surface follows the existing SDK source. It does not yet expose the new event identity, event readiness, record deletion polling, or workflow history cursor operations. Older tool results also use earlier event and deletion types. Use the current REST reference for those flows and read the client compatibility table before automating writes. Tool success alone does not establish event readiness, finished erasure, or downstream delivery.

Connect your assistant

1. Create an API key

   In the maxclicks app, open Settings, then Developers, then the API keys tab, and create one. The key is shown once, so copy it there and then. It ties the assistant to that one workspace.

2. Add the server to your client

   Configure your client with the remote server URL and send the key in its authorization header:

   https://mcp.maxclicks.ai/mcp
   Authorization: Bearer {YOUR_API_KEY}
   

   CopyCopied!

   If the client cannot send a custom header, the server also accepts https://mcp.maxclicks.ai/{YOUR_API_KEY}/mcp. Treat that complete URL as a secret.

3. Check it landed

   Ask the assistant who it is connected as. It reports the workspace and the role the key carries, which catches a key pointing at the wrong workspace before it writes anything.

What the assistant can do

It gets a tool for most of what the API can do: looking up and writing contacts and objects, firing events, building and counting segments, sending a template or a broadcast you drafted and reading back how it performed, driving workflows, and managing webhooks and suppressions.

Schemas, attributes, template and broadcast content, domains, senders and topics are read-only through the assistant. You author them in the app, and the assistant reads what you built.

Every tool inherits the key owner's workspace permissions. Suppression tools require admin; other operations require the documented read or write permission. A missing permission returns 403. See authentication.

The MCP server reference is the full picture: every tool by name, the local stdio setup with a ready-made Claude Desktop config, and how the server checks your key.

Going further

• MCP server reference: every tool, both run modes, and how key validation works.
• Build with AI: the other ways to point an agent at maxclicks, including the agent skills and the CLI (documented, not yet published to a registry).
• Authentication: how API keys are scoped.
• Rate limits and errors: what the assistant runs into when it moves too fast or gets something wrong.

Questions or problems: [email protected].