Skip to main content
Glama
DatumLabMHQ

datum-api

by DatumLabMHQ

datum-api

Part of Atlas, Datum Labs' internal data infrastructure. Start there for how the parts fit together.

Read-only HTTP API and MCP server over the Datum data platform (DatumLabMHQ/datum-models). One registry of curated tables, one list of consensus questions, served two ways so dashboards, reports and agents get the same number.

  • GET /api/v1/products — resources and their filters

  • GET /api/v1/{product}/{resource}?day=&…&limit= — rows from a curated table (latest day by default)

  • GET /api/v1/questions and GET /api/v1/ask/{id}?date= — the datum-context eval questions, answered from the canonical SQL

  • GET /api/v1/health — latest run per job, source freshness, last build

  • POST /api/mcp — MCP streamable HTTP with tools list_products, list_questions, ask, query, health

Auth: when DATUM_API_KEYS is set, send x-api-key: <key> (or Authorization: Bearer, or ?key=). Reads use the datum_reader role only. Deployed on the Datum Labs Vercel account.

Claude Code: claude mcp add --transport http datum https://<host>/api/mcp --header "x-api-key: <key>"

Related MCP Connectors

Related MCP Servers

  • F
    license
    Not graded
    quality
    D
    maintenance
    Enables read-only SQL querying and schema inspection across MSSQL, PostgreSQL, and MySQL databases via MCP tools.
    -
  • A
    license
    Not graded
    quality
    B
    maintenance
    Provides read-only access to databases for MCP-compatible AI tools, allowing schema exploration and SELECT queries without exposing credentials or risking data changes.
    80 npm
    3
    MIT
  • F
    license
    Not graded
    quality
    C
    maintenance
    Enables running read-only SQL queries and exploring DuckDB databases through MCP tools like listing tables, describing schemas, and fetching paginated data.
    -
  • F
    license
    Not graded
    quality
    C
    maintenance
    Enables read-only access to company data across PostgreSQL, MongoDB Atlas, and flat files through MCP tools, allowing AI assistants to query and retrieve information via natural language.
    -