70+ tools. One door.
The Datris MCP server is how an agent operates the platform: register pipelines, create and schedule taps, trigger jobs, query Postgres, MongoDB, Snowflake, Databricks and five vector stores, and get provenance on every answer. Runs in Docker on SSE, or locally over stdio.
Connect your agent
Paste this into Claude Desktop or Cursor's MCP config. The key is scoped: the tool catalog the agent sees is filtered to the capabilities you granted.
{
"mcpServers": {
"datris": {
"command": "uvx",
"args": ["datris-mcp-server"],
"env": {
"DATRIS_API_URL": "http://localhost:8080",
"DATRIS_API_KEY": "<scoped agent key from the Datris UI>"
}
}
}
} For a Docker deployment, point the agent at the SSE endpoint on port 3000 instead. Full tool reference in the docs.
Your AI agents are
first-class pipeline operators
Datris ships with a native MCP server. Claude, Cursor, OpenClaw, and any MCP-compatible AI agent can register pipelines, trigger jobs, and query your structured, document, and vector data in real time — all through natural conversation.
- Register pipelines and generate schemas from sample data
- Create, schedule, and run AI-generated taps
- Ingest documents into vector databases (extract → chunk → embed)
- Upload data for processing
- Trigger and monitor pipeline jobs
- Profile data and get AI insights
- Semantic search across vector databases
- Query PostgreSQL and MongoDB directly
- Get an answer without landing a table — Live Read pipelines return validated rows straight to the agent
- Run the built-in doctor to diagnose the platform before retrying a failed run
- Manage credentials via Vault — without ever holding the key