Data · Local MCP server
DataRaum
Pre-computed metadata context engine for AI-driven data analytics.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.dataraum/dataraum- Version
- 0.2.1
- Status
- Active
- Category
- data
- Transport
- stdio (local process)
- Package
- PyPI
- Published
- 2026-04-17
- Updated
- 2026-04-17
- Publisher
- dataraum (GitHub)
- Repository
- github.com/dataraum/dataraum
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPIruntime: uvx | dataraum | 0.2.1 | stdio |
How to connect DataRaum
DataRaum runs locally from a Python package published to PyPI: dataraum version 0.2.1. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install — the usual command is uvx dataraum. It reads these environment variables: ANTHROPIC_API_KEY (required, secret) and DATARAUM_HOME; set them in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"dataraum": {
"command": "uvx",
"args": [
"dataraum"
],
"env": {
"ANTHROPIC_API_KEY": "<secret>",
"DATARAUM_HOME": "<value>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More data servers
| Server | Runs |
|---|---|
| Datanika MCPRead-only-by-default MCP for Datanika: browse data, run dbt transforms, manage ELT pipelines. | Local · stdio |
| Dataprev: Fator Acidentário de Prevenção (FAP)Dataprev: Fator Acidentário de Prevenção (FAP), official-source lookup. Platform-hosted, pay per que. | Remote · HTTP |
| DataPulseRead-only discovery for 418 Malaysian public datasets with freshness, licence, and provenance. | Remote · HTTP |
| DataQuollAustralian public data as MCP tools: incidents, gauges, declarations, industry calendars, archive. | Remote · HTTP |
| Dataroia Data TrustVérification B2B française: SIRET, SIRENE, dirigeants RNE, santé d'entreprise. Hébergé en France. | Remote · HTTP |
| DataScoop public dataOfficial UK, US and Australia public datasets as filtered CSV, REST API and MCP for AI agents. | Remote & Local · HTTP, stdio |
| Dataset Aggregate & PivotGROUP BY and pivot tables for JSON rows: 11 functions, date buckets, top N, totals, messy numbers. | Remote · HTTP |
| Dataset Aggregate, Group By & PivotReturns GROUP BY and pivot tables for any Apify dataset, file or Google Sheet by URL, or JSON... | Remote · HTTP |