Skip to content
MetaxisData
中文

Agent integration

Built for a program to call

The mxd CLI gives an agent one JSON document per command, stable exit codes, and device login. With MCP enabled, the registry is also available as read-only tools behind an OAuth 2.1 authorization server.

A metadata platform is only useful to an agent if the answers are machine-shaped. Both entry points are read-only, addressed by name rather than by internal ids, and audited.

mxd — one JSON document per command

Every command writes exactly one JSON document to stdout; progress, warnings and errors go to stderr. Failures carry a stable code and a stable exit status, so a caller decides what to do next without parsing prose. mxd skill install drops the matching instructions where an agent runtime finds them. 

$ mxd lineage sql --file etl.sql --depth 2
{
  "results": [
    {
      "scopeName": "dev",
      "scopeGuid": "1;shop",
      "relations": [
        {"sourceGuid": "1;shop;;orders", "sourceColumn": "amount",
         "targetGuid": "1;shop;;order_daily", "targetColumn": "amount",
         "isTemp": false}
      ],
      "warnings": []
    }
  ],
  "warnings": []
}

MCP — the registry as read-only tools

Enable the endpoint in Settings → General (it needs the workspace external URL). An MCP client is told where to authorize, registers itself, and runs the PKCE flow; the decision is recorded on a consent page. Nothing here writes. 

{
  "mcpServers": {
    "metaxisdata": {
      "type": "http",
      "url": "https://mx.example.com/mcp"
    }
  }
}

Known limits

  • Nothing here writes: the CLI and the MCP surface only read the registry.
  • Scopes are never persisted — which instance a statement belongs to is the caller's decision, passed per invocation.

Read more