Data Aggregator Mcp
by musharnacommunityv0.20.0
2
This MCP server searches and resolves research datasets and papers across archives, omics registries, literature sources, and HuggingFace datasets through a single normalized model. It can also fetch supported files to disk with checksum or content-type verification, and inspect remote tabular files in place for some sources.
From the registry: Find & fetch research datasets across Zenodo, DataCite, NCBI omics, and literature.
Install & configure
Prerequisites
- optionalInstall uvInstall the uv Python package manager/runtime to run the server without a local package install using uvx.
https://docs.astral.sh/uv/$ uv --version - optionalOptional NCBI API keyCreate an NCBI API key to raise the NCBI E-utilities rate limit used by omics, literature, and taxonomy lookups.
- optionalOptional Unpaywall emailProvide an email address for Unpaywall to enable the fallback leg of literature full-text retrieval.https://unpaywall.org/products/api
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `data-aggregator-mcp` MCP server into my current AI client (that's you).
Optional prerequisites:
- Install uv — Install the uv Python package manager/runtime to run the server without a local package install using uvx. Run: `uv --version` (https://docs.astral.sh/uv/)
- Optional NCBI API key — Create an NCBI API key to raise the NCBI E-utilities rate limit used by omics, literature, and taxonomy lookups.
- Optional Unpaywall email — Provide an email address for Unpaywall to enable the fallback leg of literature full-text retrieval. (https://unpaywall.org/products/api)
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["data-aggregator-mcp"]
- optional environment variables:
- `NCBI_API_KEY`: Optional NCBI API key to raise the NCBI E-utilities rate limit (3 to 10 req/s) for omics, literature, and taxonomy lookups. (example: `<your-ncbi-api-key>`)
- `UNPAYWALL_EMAIL`: Optional email address to enable the Unpaywall fallback for literature full-text retrieval. (example: `<your-email@example.com>`)
Note: Preferred portable install path is `uvx data-aggregator-mcp`. The server also supports `pip install data-aggregator-mcp` and running `data-aggregator-mcp` or `python -m data_aggregator_mcp`. The optional `operate` tool requires installing the extra `data-aggregator-mcp[operate]`, but the base server install and stdio config are unchanged.
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: Preferred portable install path is `uvx data-aggregator-mcp`. The server also supports `pip install data-aggregator-mcp` and running `data-aggregator-mcp` or `python -m data_aggregator_mcp`. The optional `operate` tool requires installing the extra `data-aggregator-mcp[operate]`, but the base server install and stdio config are unchanged.
Tools (5)
search
Fan out across configured sources in parallel to find matching DataResource records, with filtering, pagination, and optional organism synonym expansion.
resolve
Return a full record for an ID, including file manifests, links, access/license info, citations, trust signals, and optional Croissant or RO-Crate output.
fetch
Download resolved files to disk with size guards and checksum/content-type verification, optionally extracting archives.
list_sources
List wired sources and their capabilities, including supported kinds, filters, fetchability, and rate limits.
operate
Inspect or query a remote tabular file in place with schema, preview, head, or read-only SQL operations.
Environment variables
NCBI_API_KEYRaises NCBI E-utilities rate limits for omics, literature, and taxonomy lookups.UNPAYWALL_EMAILUsed for Unpaywall-based open-access full-text lookup.EMBEDDING_API_BASENeeded to enable semantic ranking in search.Packages
data-aggregator-mcp
pypiv0.20.0transport: stdio
Details
- Language
- Python
- License
- MIT
- Released
- Jun 2, 2026
- Last commit
- Jul 27, 2026
- Registry name
- io.github.musharna/data-aggregator-mcp
Categories
Related Servers
Labelhead Artist Momentum
Trending hip-hop artist momentum scores across four cultural dimensions.
74.7k
PostHog MCP Server
Official PostHog MCP Server for product analytics, feature flags, experiments, and more.
37.3k
Openmetadata Mcp
Official OpenMetadata MCP: governed context and business semantics for AI assistants and agents.
14.6k