Data Aggregator MCP Server

One MCP server to find and fetch research data across archives, omics registries, and literature - behind a single normalized model. Its 26 documented tools cover shared, data. It runs locally over stdio via the published package.

People connecting science & health tools to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-08-23 · ★ 2 · #20 OF 60 MAINTAINED SCIENCE & HEALTH · VERIFIED 2026-08-25

MIT · Python servers · how we verify → /methodology

01 · Install Data Aggregator

before you install - you'll need

Set DATA_AGGREGATOR_MCP_LIVE before connecting. NCBI_API_KEY is optional or environment-specific per the README.

Claude Code

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

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "musharna-data-aggregator-mcp": {
      "command": "uvx",
      "args": [
        "data-aggregator-mcp"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package data-aggregator-mcp - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.musharna is GitHub-verified and matches the repo owner

03 · What Data Aggregator can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can find datasets for a topic, optionally scoped to an organism, and find the datasets / accessions behind a paper.

Capability map

Tools grouped from the project's README - what Data Aggregator lets an agent do.

read & search

2 tools - e.g. Zenodo, SRA, GEO, DataONE (Member-Node objects,; walk the end-to-end search → resolve → fetch flow.

Fetchable · search_resolve_fetch

Shared

2 tools - e.g. same BioProject/SRA/GEO accession on ≥2 records → joinable key.; same doi/pmid/pmcid across records → same work / paper↔data link.

shared_accession · shared_identifier

Data

2 tools - e.g. find datasets for a topic, optionally scoped to an organism.; find the datasets / accessions behind a paper.

find_data · data_behind_paper

Organism

1 tool - e.g. expand the query with NCBI-Taxonomy synonyms; the expansion is

organism

Sources

1 tool - e.g. restrict the fan-out, e.g. ["omics"].

sources

Size

1 tool - e.g. max results (1–50).

size

Kind

1 tool - e.g. keep only dataset / sequencing_run / study / publication /

kind

Rank

1 tool - e.g. relevance (default) or semantic (re-rank the fetched page by

rank

Latest releases

v0.45.3 · 2026-07-28

v0.45.3 · Security fix, and a correction to v0.45.2. Take this instead of 0.45.2 if you · run the HTTP transport, or if you call operate/fetch on records you did not · publish yourself. · Fixed · A redirect bypassed…

v0.45.2 · 2026-07-28

v0.45.2 · Security fix. Upgrade from 0.45.1 if you run the HTTP transport, or if you call · operate/fetch on records you did not publish yourself. · Fixed · A record's file URL could make the server read addresses the…

v0.45.1 · 2026-07-28

v0.45.1 · Security fix. Upgrade from 0.45.0 if you rely on licence verdicts. · Fixed · A hostile licence URL could mint a permissive verdict. host_matches already · rejected a domain sitting in someone else's path, but…

04 · Who maintains Data Aggregator

Data Aggregator is maintained by musharna. We track 7 MCP servers from musharna - 7 actively maintained, 11 combined GitHub stars, oldest repo from May 2026. Full record: all servers from musharna.

05 · Facts

repository: github.com/musharna/data-aggregator-mcp
category: science & health - ranked #20 of 60 actively-maintained science & health servers as of 2026-08-25.
release cadence: 10+ releases in the last 90 days (latest 2026-07-28)
registry: io.github.musharna/data-aggregator-mcp (active, first published 2026-05-30 · 35 versions)
packages: pypi:data-aggregator-mcp

06 · Data Aggregator FAQ

Is Data Aggregator still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-23 and it shipped 10+ releases in the last 90 days. We re-verify nightly.

What can Data Aggregator do?

With this server connected, an agent can find datasets for a topic, optionally scoped to an organism, and find the datasets / accessions behind a paper.

How do I install Data Aggregator?

Run `uvx data-aggregator-mcp`. The README documents 2 environment variables (NCBI_API_KEY, DATA_AGGREGATOR_MCP_LIVE) to set first. Set DATA_AGGREGATOR_MCP_LIVE before connecting. NCBI_API_KEY is optional or environment-specific per the README. You can also paste the ready-made client config above.

Does Data Aggregator run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Data Aggregator

Alternatives to Data Aggregator

Maintained science & health servers if Data Aggregator isn't the fit.

More science & health MCP servers · Pubcrawl · Redacta MCP · DICOM/HL7/FHIR Interoperability MCP Server · Omophub MCP · Kaiord

More Python MCP servers · Jobd · Ldraw MCP · Plant Genomics · Openshorts · Agent SUMO · see all