Connect an AI Agent

Zingasuite is AI-native: any AI agent that speaks the Model Context Protocol (MCP) can connect to your account and work inside it — read your catalog, create and update products, import and look up orders, adjust inventory, send WhatsApp messages, and search your own documentation.

Concretely, that means you can open Claude Code, Claude Desktop, Cursor, or your own agent built on any MCP-capable SDK, point it at Zingasuite, and ask it to "list my low-stock products and draft restock quantities" or "import this order" — and it does the work through the same API the console uses.

What is MCP?

MCP is an open standard for connecting AI assistants to external systems through a common set of tools, resources, and prompts. Zingasuite runs a remote MCP server — you don't install anything on a server; you just tell your AI client the server's URL and give it an API key.

The server

https://mcp.zingasuite.com/mcp

It's a remote, Streamable-HTTP MCP server. You authenticate with a Zingasuite zk_ API key (the same keys used for the REST API). What the agent is allowed to do is bounded by that key's scopes — so you can hand an agent a read-only key with confidence, or a read-write key when you want it to make changes.

MCP vs the REST API

Zingasuite also has a plain REST API (/papi/v1). Same data, same permissions — pick whichever fits:

MCP — for AI agents. The agent discovers the available tools automatically and calls them conversationally. No client code to write.
REST — for your own integrations and scripts, where you control the requests.

Next steps

Authentication & keys — create the API key your agent will use.
Connect your client: Claude Code · Claude Desktop · Cursor & others · Local npx bridge.
Tool catalog — what the agent can do.
Safety & read-only agents — keeping agents least-privileged.

The fastest path: open Console → Settings → Connect AI Agents, which generates a key and shows ready-to-paste config for each client.