Data Aggregator MCP Server

data-aggregator-mcp

Search 20 research-data sources at once (data archives, omics repositories and papers) and get one list back. Organism, disease and tissue names are expanded with their synonyms in the 12 sources that accept them, records that share a DOI are collapsed to one, and downloads are checked against the source's checksum where it publishes one.

mcp-name: io.github.musharna/data-aggregator-mcp

Install

Claude Code:

claude mcp add data-aggregator -- uvx data-aggregator-mcp

VS Code and Cursor: the buttons above. Any other MCP client: run uvx data-aggregator-mcp as a stdio server.

Claude Desktop (claude_desktop_config.json) and most other clients:

{
  "mcpServers": {
    "data-aggregator": {
      "command": "uvx",
      "args": ["data-aggregator-mcp"],
      "env": { "NCBI_API_KEY": "your-optional-key" }
    }
  }
}

With pip:

pip install data-aggregator-mcp
data-aggregator-mcp        # or: python -m data_aggregator_mcp

operate (SQL and previews over remote files) needs an optional extra: pip install "data-aggregator-mcp[operate]".

What you can ask

"Find transcriptomes for Orobanche aegyptiaca." The species has been renamed. NCBI Taxonomy maps it to Phelipanche aegyptiaca, and the sources that accept synonyms match both names (the demo above).

"What data came out of this paper?"

resolve("pubmed:40098680")
  links  geo:GSE284240, bioproject:PRJNA1198054, and 18 sra: experiments
  files  PMC11910882.xml   (open-access full text)

"Can I train a model on this dataset?"

resolve("hf:scikit-learn/iris", use="ml-training")
  license_compat  ALLOW: "CC0-1.0 grants the permission(s) required for
                  ml-training: commercial-use, modifications"

The verdict is read from the record's licence metadata. It is advice, not a legal opinion.

resolve also renders citations in any CSL style, checks Crossref for retractions, scores FAIRness, and exports Croissant or RO-Crate. relate reports how a set of records connect (a shared accession, DOI or explicit link).

How a search runs

A source that fails is named in the result's errors, never dropped silently.

Compared with other servers

— means the project's README doesn't describe it (READMEs read 2026-10-04). Where they are ahead: BioMCP reaches clinical trials, ChEMBL and AlphaFold, which this server doesn't; ToolUniverse covers far more ground overall; paper-search-mcp covers far more literature sources; Mobus also compares datasets and checks schema compatibility. More detail: docs/POSITIONING.md.

Sources

¹ Dryad downloads are token / bot-challenge gated, so fetch returns an error; resolve still lists the files.

² No upstream checksum, so fetch does not verify these bytes. It still returns an error on an HTTP error or when the download exceeds max_bytes.

³ No upstream checksum. Files declared as PDF or XML (literature full text, and data.gov distributions with that mediaType) get an HTML sniff: an HTML login or paywall page served in their place returns an error. Other files are not checked.

⁴ Only records that carry a downloadable file (a GBIF Darwin Core Archive, a data.gov distribution URL); metadata-only records are discovery-only.

⁵ Discovery-only: granule downloads need an Earthdata login, which is not wired. resolve returns the DOI and a data-access portal link.

Reference

Every tool and parameter, the HTTP transport (--transport http), and the environment variables: docs/reference.md.

Develop

uv venv && uv pip install -e ".[dev]"
uv run pytest -q
uv run ruff check src tests
DATA_AGGREGATOR_MCP_LIVE=1 uv run pytest -k live -q   # real-API probes

The README demo (examples/assets/demo.svg) is recorded from live calls by examples/_demo_search.py; its header has the commands to re-record it.

License

MIT — see LICENSE.