datris-mcp-server 1.5.2

MCP server for AI-driven data pipeline operations — ingest, validate, transform, analyze, and query data. 32 tools covering ETL, AI data quality, vector search, PostgreSQL, MongoDB, Kafka, S3/MinIO, HashiCorp Vault, Qdrant, Weaviate, Milvus, Chroma, pgvector.

Datris MCP Server

MCP (Model Context Protocol) server for the Datris AI Agent-Native Data Platform. Enables AI agents (Claude Desktop, Claude Code, Cursor, and custom frameworks) to natively interact with the platform — discover data, create pipelines, upload files, monitor jobs, search vector databases, query structured data, and answer questions with AI.

Install

pip install datris-mcp-server

Usage

stdio mode (Claude Desktop / Claude Code)

PIPELINE_URL=http://localhost:8080 datris-mcp-server

Or run directly:

PIPELINE_URL=http://localhost:8080 python server.py

SSE mode (Docker / remote agents)

PIPELINE_URL=http://localhost:8080 datris-mcp-server --sse --port 3000

Docker

The MCP server starts automatically with docker compose up in SSE mode on port 3000.

Configuration

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "datris": {
      "command": "datris-mcp-server",
      "env": {
        "PIPELINE_URL": "http://localhost:8080"
      }
    }
  }
}

Claude Code

Add to .mcp.json in your project root:

{
  "mcpServers": {
    "datris": {
      "command": "datris-mcp-server",
      "env": {
        "PIPELINE_URL": "http://localhost:8080"
      }
    }
  }
}

Environment Variables

Variable	Default	Description
PIPELINE_URL	http://localhost:8080	Datris pipeline server URL
PIPELINE_API_KEY	(empty)	API key if pipeline has key validation enabled

Tools

30+ tools across these categories:

• Pipeline Management — create, list, get, delete pipelines; upload files; monitor jobs
• Vector Search — semantic search across Qdrant, Weaviate, Milvus, Chroma, pgvector
• Database Query — read-only SQL queries (PostgreSQL) and MongoDB queries
• Metadata Discovery — explore databases, schemas, tables, columns, collections
• AI — RAG-powered question answering
• System — health checks, version info

See the full documentation at docs/mcp.md.

License

Apache 2.0