Data Aggregator
Find & fetch research datasets across 21 archives, omics registries, and literature sources.
Open the source (opens github.com) https://github.com/musharna/data-aggregator-mcp
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
- Needs credentials: DATA_GOV_API_KEY, EMBEDDING_API_KEY, LLM_API_KEY, NCBI_API_KEY. Use a key with the least access you can.
What it is
MCP servers from io.github.musharna.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
pypi package (stdio)
data-aggregator-mcp@0.76.0
From the server's entry in the official MCP Registry
Settings it asks for
NCBI_API_KEYsecret · Optional NCBI E-utilities API key; raises the rate limit 3->10 req/s for omics, literature, and taxonomy lookups.LLM_API_BASE· Base URL of an OpenAI-compatible /chat/completions endpoint; enables search(understand=true) and search(multi_query=true).LLM_API_KEYsecret · Bearer token for the LLM endpoint (LLM_API_BASE); omit for keyless local servers.LLM_MODEL· Model name passed to the LLM endpoint (default: gpt-4o-mini); set to whatever your endpoint serves.EMBEDDING_API_BASE· Base URL of an OpenAI-compatible /embeddings endpoint; enables search(rank=semantic) re-ranking.EMBEDDING_API_KEYsecret · Bearer token for the embeddings endpoint (EMBEDDING_API_BASE); omit for keyless local servers.EMBEDDING_MODEL· Model name passed to the embeddings endpoint (default: text-embedding-3-small).DATA_GOV_API_KEYsecret · Optional api.data.gov key for the data.gov source; without it requests fall back to the shared public DEMO_KEY, which is aggressively rate-limited.UNPAYWALL_EMAIL· Email address sent to the Unpaywall API; required to enable the Unpaywall PDF fallback leg of literature full-text retrieval.NCBI_EMAIL· Contact address sent to NCBI's ID converter; falls back to UNPAYWALL_EMAIL when unset.DATAVERSE_BASE_URL· Resolve Dataverse DOIs against a different installation (default: https://dataverse.harvard.edu).CACHE_TTL_SECONDS· Resolve-cache lifetime in seconds (default: 3600); an unparseable value falls back to the default.
Related
-
Official data with free samples, provenance, aggregations, freshness and agent-ready insights.
-
data-aggregator-mcp
MCP serversUnified data server: stocks, crypto, news, weather, web scraping, FX rates in one MCP
data-aggregator-mcp@1.1.4 -
Apify MCP server
MCP serversLets an agent run Apify's ready-made scrapers to pull data from websites, search engines, maps and social platforms.
-
US Building Permit Aggregator
MCP serversPull recent building permits from 9 US cities in a unified schema from official open-data portals.
-
open-health-sync
MCP serversOpen source health data aggregator and self-hosted Terra alternative. One API for wearable data from Apple Health, Health Connect, Oura, WHOOP, Withings, Fitbit, Dexcom and more: REST, FHIR R4, Open mHealth, webhooks, CSV/Parquet and a read-only MCP server. One Go binary plus Postgres. AGPL-3.0.
git clone https://github.com/soma-intelligence/open-health-sync.git -
jDataMunch MCP
MCP serversTabular data retrieval. Index CSV/Excel, query rows, aggregate. 99%+ savings vs raw file reads.
jdatamunch-mcp@1.33.0