Dataraum

Name: Dataraum
Author: dataraum

by dataraumcommunityv0.2.1

DataRaum is an MCP server that analyzes tabular data sources like CSV, Parquet, and JSON to generate rich metadata context for AI-assisted data analysis. It supports session-based exploration, quality measurement, natural-language querying, and SQL execution over the analyzed data.

From the registry: Pre-computed metadata context engine for AI-driven data analytics

GitHub Repository

Install & configure

Prerequisites

required
Install DataRaum
Install the DataRaum Python package so the MCP server executable is available.
```
$ pip install dataraum
```
https://pypi.org/project/dataraum/
required
Set Anthropic API key
Semantic analysis requires an Anthropic API key. In default usage, this is needed for LLM-powered semantic analysis.
```
$ export ANTHROPIC_API_KEY="<your-anthropic-api-key>"
```

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `dataraum` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install DataRaum** — Install the DataRaum Python package so the MCP server executable is available. Run: `pip install dataraum` (https://pypi.org/project/dataraum/)
- **Set Anthropic API key** — Semantic analysis requires an Anthropic API key. In default usage, this is needed for LLM-powered semantic analysis. Run: `export ANTHROPIC_API_KEY="<your-anthropic-api-key>"`

Canonical MCP server config (stdio transport):
- command: `dataraum-mcp`
- args: []
- required environment variables:
  - `ANTHROPIC_API_KEY`: Anthropic API key used for semantic analysis. (example: `<your-anthropic-api-key>`)

Note: The README shows the MCP server launched via the `dataraum-mcp` command after installing the `dataraum` package. It also mentions LLM provider configuration in `config/llm/config.yaml`, but no MCP config-file command-line arguments or additional environment variables are documented in the provided README.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: The README shows the MCP server launched via the `dataraum-mcp` command after installing the `dataraum` package. It also mentions LLM provider configuration in `config/llm/config.yaml`, but no MCP config-file command-line arguments or additional environment variables are documented in the provided README.

Tools (7)

begin_session

Start an investigation session with a contract

add_source

look

Explore data structure, relationships, and semantic metadata

measure

Measure entropy scores, readiness, and data quality

query

Natural language query against the data

run_sql

Execute SQL directly with export support

end_session

Archive workspace and end the session

Environment variables

ANTHROPIC_API_KEYrequiredAPI key required for semantic analysis and LLM-powered metadata generation

Packages

dataraum

pypiv0.2.1transport: stdio

Details

Language: Python
License: Apache-2.0
Released: Apr 17, 2026
Last commit: Jun 5, 2026
Registry name: io.github.dataraum/dataraum

Related Servers

Labelhead Artist Momentum

Trending hip-hop artist momentum scores across four cultural dimensions.

74.4k

PostHog MCP Server

Official PostHog MCP Server for product analytics, feature flags, experiments, and more.

37.2k

Openmetadata Mcp

Official OpenMetadata MCP: governed context and business semantics for AI assistants and agents.

14.5k