MCP Server¶
Connecting an AI client to Qualytics?
Claude Desktop, Claude Code, Cursor, ChatGPT, and other MCP-compatible clients connect to your Qualytics deployment directly, with no CLI required. See Connecting External AI Clients for the setup steps for each client.
The CLI includes qualytics mcp serve, a local bridge to the Model Context Protocol (MCP) server built into your Qualytics deployment. Use it when:
- The client only supports MCP servers that run as a local command (the
stdiotransport) and cannot connect to an HTTP endpoint. - You already logged in with the CLI and want the assistant to reuse that session instead of managing a separate token.
Start the Server¶
The command reads the URL, token, and SSL setting saved by the CLI login (or the QUALYTICS_URL and QUALYTICS_TOKEN environment variables) and forwards every tool call to your deployment's MCP endpoint. MCP clients normally launch this command in the background; you rarely run it by hand.
Options¶
| Option | Type | Default | Required | Description |
|---|---|---|---|---|
--transport, -t |
TEXT | stdio |
No | Transport protocol: stdio or streamable-http |
--host |
TEXT | 127.0.0.1 |
No | Host for streamable-http transport |
--port, -p |
INTEGER | 8000 | No | Port for streamable-http transport |
Register the Bridge in a Client¶
Register qualytics mcp serve as a command-based (stdio) MCP server. In Claude Code, for example:
Other clients follow the same pattern: the command is qualytics and the arguments are mcp serve. Check the client's documentation for where it stores command-based MCP servers.
HTTP Transport¶
To expose the bridge over the network, for example when the assistant runs on a different machine than the CLI:
Then point the client at http://<host>:8000. The bridge carries the full permissions of your CLI token, so restrict network access accordingly.
Available Tools¶
The bridge exposes the same tools as your deployment's MCP server, so the list is always current with your Qualytics version. See the MCP Deep Dive for what those tools can do. It adds one local tool, auth_status, which reports the CLI's configured URL, token validity, and expiry so the assistant can confirm the CLI is set up before making calls.
Prerequisites
The bridge uses your existing CLI authentication. Complete browser login or manual token setup before starting it.