Datris MCP Server

AI Agent-Native Data Platform — ingest, validate, transform, and query data.

Remote serverstreamable-httpPython

What is the Datris MCP server?

Datris MCP server exists for a simple reason — assistants are far more useful when they can act on Datris directly instead of describing what you should do. AI Agent-Native Data Platform — ingest, validate, transform, and query data.

What you get

Ingest, validate, transform, store, and retrieve your data — whether you're an AI agent talking through MCP or a developer writing config. One platform for both.

  • Agent-native — — Built-in MCP server with 47 tools. Claude, Cursor, and any MCP-compatible agent can operate pipelines through natural conversation
  • Taps — — AI-generated Python scripts that fetch data from external sources (APIs, web scraping, databases) and push it into pipelines. Describe what you want, Datris generates the script. Includes AI diagnosis, CRON scheduling, and credentials via Vault
  • AI at every stage — — AI data quality, AI transformations, AI schema generation, AI profiling, AI error explanation, natural language queries, RAG
  • No vendor lock-in — — 100% open-source infrastructure (MinIO, PostgreSQL, MongoDB, Kafka, Vault). Runs anywhere Docker does
  • Configuration-driven — — Define pipelines through JSON. No code required

Setting it up

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

What the assistant can call

Once Datris is connected, these are the calls the assistant has available:

  • Agent-native — Built-in MCP server with 47 tools. Claude, Cursor, and any MCP-compatible agent can operate pipelines through natural conversation
  • Taps — AI-generated Python scripts that fetch data from external sources (APIs, web scraping, databases) and push it into pipelines. Describe what you want
  • Configuration-driven — Define pipelines through JSON. No code required
  • Feature — Description
  • Service — Purpose
  • MinIO — S3-compatible object store for file staging and data output
  • PostgreSQL — Default structured destination, also hosts pgvector for RAG
  • MongoDB — Configuration store, job status tracking, metadata
  • ActiveMQ — File notification queue, pipeline event notifications
  • TEI — Text Embeddings Inference sidecar (BAAI/bge-m3) — local vector embeddings when you're not using OpenAI embeddings

Configuration and credentials

You will need 2 environment variables: ANTHROPIC_API_KEY, OPENAI_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Before you rely on it

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 10 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Datris.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the datris mcp server does with a few real requests.

Choosing this one

This sits in the database access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Datris's toolset — Agent-native, Taps, Configuration-driven and 7 more — is a fair guide to whether it matches your workflow. It is maintained by datris; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Datris's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
Agent-nativeBuilt-in MCP server with 47 tools. Claude, Cursor, and any MCP-compatible agent can operate pipelines through natural conversation
TapsAI-generated Python scripts that fetch data from external sources (APIs, web scraping, databases) and push it into pipelines. Describe what you want, Datris generates the script. Includes AI diagnosis, CRON scheduling, a
Configuration-drivenDefine pipelines through JSON. No code required
FeatureDescription
ServicePurpose
MinIOS3-compatible object store for file staging and data output
PostgreSQLDefault structured destination, also hosts pgvector for RAG
MongoDBConfiguration store, job status tracking, metadata
ActiveMQFile notification queue, pipeline event notifications
TEIText Embeddings Inference sidecar (BAAI/bge-m3) — local vector embeddings when you're not using OpenAI embeddings

How to install the Datris MCP server

{
  "mcpServers": {
    "datris": {
      "command": "npx",
      "args": ["-y", "mcp-remote"],
      "env": {
        "ANTHROPIC_API_KEY": "your-value",
        "OPENAI_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
ANTHROPIC_API_KEYCredential the server authenticates with.Yes
OPENAI_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Datris to Agent-native.
  • Use Datris to Taps.
  • Use Datris to Configuration-driven.

Frequently asked questions

It connects Datris to MCP-compatible AI assistants such as Claude and Cursor, exposing 10 tools (Agent-native, Taps, Configuration-driven, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Datris directly.