Atlas

io.github.AtlasDevHQ/atlas·v0.0.2·Analytics

Quality Score

/100

Atlas is a YAML-defined semantic layer for analytics — authored by humans, consumed by AI agents.

Repository →Website →

§01 Install

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "atlas": {
      "command": "npx",
      "args": [
        "-y",
        "@useatlas/mcp"
      ],
      "env": {
        "ATLAS_DATASOURCE_URL": "<your-atlas_datasource_url>",
        "ATLAS_PROVIDER": "<atlas_provider>",
        "ATLAS_API_URL": "<atlas_api_url>"
      }
    }
  }
}

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "atlas": {
      "command": "npx",
      "args": [
        "-y",
        "@useatlas/mcp"
      ],
      "env": {
        "ATLAS_DATASOURCE_URL": "<your-atlas_datasource_url>",
        "ATLAS_PROVIDER": "<atlas_provider>",
        "ATLAS_API_URL": "<atlas_api_url>"
      }
    }
  }
}

Cline (cline_mcp_settings.json)

npx -y @useatlas/mcp

§02 Environment variables

ATLAS_DATASOURCE_URL

secret

Analytics datasource URL (postgres, mysql, clickhouse, snowflake, duckdb, bigquery, salesforce). Optional — falls back to a bundled NovaMart SQLite demo when unset.

ATLAS_PROVIDER

LLM provider: anthropic, openai, bedrock, ollama, openai-compatible, gateway. Optional — the MCP server does not call an LLM directly (the client does); set this only if you also run Atlas's chat or scheduler.

ATLAS_API_URL

URL of a running Atlas API. Optional — defaults to http://localhost:3001. When set, the MCP server inherits the API's connections, semantic layer, and governance.

§03 MCP Quality Score · methodology

freshness

completeness

installability

documentation

stability

§04 Alternatives in Analytics

Alpic

ai.alpic.mcp/alpic-mcp

Manage your projects, debug deployment, and check analytics for any MCP server you host with Alpic

HAPI Strava MCP Server

ai.com.mcp/strava

Strava MCP tools for AI: athletes, activities, segments, clubs, routes. Powered by HAPI MCP server.

ai.mcpanalytics/analytics

Analytics for business data: upload CSV or connect GA4/GSC, run ML/stats, get HTML reports.