MCP server
Understand DataMaker’s built-in MCP services and external-client requirements.
DataMaker exposes tools through the Model Context Protocol (MCP). The in-product agent is configured with the services it needs automatically; you do not need to install a separate MCP package to use chat.
Current architecture
The DataMaker API hosts Streamable HTTP MCP endpoints. Metadata and execution are separate tool surfaces:
| Endpoint | Purpose |
|---|---|
/mcp | Discover/manage assets and use selected generation helpers. |
/mcp-exec | Generation, execution and data operations. |
/mcp-plan | Create reviewable plans. |
/mcp-exec/plan-run | Execute supported plans and inspect run reports. |
/mcp-exec/{namespace} | System tools, such as SAP, Tosca and Atlassian, when registered. |
The configured execution host can differ from the metadata API host in desktop team mode. Use the URLs supplied by your deployment, not an assumed public hostname for every service.
Authentication
The built-in HTTP transport uses a session JWT in Authorization: Bearer, with X-Project-Id and X-Team-Id context. A REST API key in X-API-Key is not a substitute for this transport's session authentication.
For external clients, your administrator must provide a supported endpoint and session-authentication method. The available tools and permissions depend on the service, deployment and caller. See Clients setup.
Older standalone package
The separate datamaker-mcp repository describes an older stdio server. Its package @automators/datamaker-mcp is currently unpublished on npm. The old pipx install datamaker-mcp and unscoped npx datamaker-mcp instructions are not a supported setup for the current built-in server.
Use DataMaker chat for the integrated experience, or the REST API and SDKs for API-key automation.
Working with tools
Start with read-only discovery: list the active project's templates or inspect a saved plan. Read the announced tool schema before invoking it; tool names, arguments and output shapes differ across services. Review the target and data volume before writes, and honor any approval request.
See Tool catalogue for the main tool groups.