Data Aggregator MCP Server
io.github.musharna/data-aggregator-mcp
What this kind of tool is for
- Query, inspect, or seed a database without writing a one-off script.
- Let your agent look up schema details before it writes migration code.
- Move a small dataset between tools without leaving the terminal.
How to compare servers like this
- Engine match:
- Confirm it speaks your exact database and version, not just the family.
- Access scope:
- Read-only connections are the safe default — start there before granting writes.
- Safety rails:
- Check whether destructive statements need an explicit confirmation before they run.
- Maintenance signal:
- Database drivers change; a recently updated tool is less likely to break mid-query.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the Data Aggregator MCP server?
Find & fetch research datasets across 17 archives, omics registries, and literature sources.
How to install Data Aggregator
Copy-paste configuration for popular MCP clients.
NCBI_API_KEYsecretOptional NCBI E-utilities API key; raises the rate limit 3->10 req/s for omics, literature, and taxonomy lookups.
LLM_API_BASEBase URL of an OpenAI-compatible /chat/completions endpoint; enables search(understand=true) and search(multi_query=true).
LLM_API_KEYsecretBearer token for the LLM endpoint (LLM_API_BASE); omit for keyless local servers.
LLM_MODELModel name passed to the LLM endpoint (default: gpt-4o-mini); set to whatever your endpoint serves.
EMBEDDING_API_BASEBase URL of an OpenAI-compatible /embeddings endpoint; enables search(rank=semantic) re-ranking.
EMBEDDING_API_KEYsecretBearer token for the embeddings endpoint (EMBEDDING_API_BASE); omit for keyless local servers.
EMBEDDING_MODELModel name passed to the embeddings endpoint (default: text-embedding-3-small).
DATA_GOV_API_KEYsecretOptional 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_EMAILEmail address sent to the Unpaywall API; required to enable the Unpaywall PDF fallback leg of literature full-text retrieval.
NCBI_EMAILContact address sent to NCBI's ID converter; falls back to UNPAYWALL_EMAIL when unset.
DATAVERSE_BASE_URLResolve Dataverse DOIs against a different installation (default: https://dataverse.harvard.edu).
CACHE_TTL_SECONDSResolve-cache lifetime in seconds (default: 3600); an unparseable value falls back to the default.
{
"mcpServers": {
"data-aggregator-mcp": {
"command": "uvx",
"args": [
"data-aggregator-mcp"
],
"env": {
"NCBI_API_KEY": "<YOUR_NCBI_API_KEY>",
"LLM_API_BASE": "<YOUR_LLM_API_BASE>",
"LLM_API_KEY": "<YOUR_LLM_API_KEY>",
"LLM_MODEL": "<YOUR_LLM_MODEL>",
"EMBEDDING_API_BASE": "<YOUR_EMBEDDING_API_BASE>",
"EMBEDDING_API_KEY": "<YOUR_EMBEDDING_API_KEY>",
"EMBEDDING_MODEL": "<YOUR_EMBEDDING_MODEL>",
"DATA_GOV_API_KEY": "<YOUR_DATA_GOV_API_KEY>",
"UNPAYWALL_EMAIL": "<YOUR_UNPAYWALL_EMAIL>",
"NCBI_EMAIL": "<YOUR_NCBI_EMAIL>",
"DATAVERSE_BASE_URL": "<YOUR_DATAVERSE_BASE_URL>",
"CACHE_TTL_SECONDS": "<YOUR_CACHE_TTL_SECONDS>"
}
}
}
}Related MCP servers

jobd
Self-hostable GPU-aware job broker: submit, route by VRAM, babysit jobs across machines via MCP.

ldraw-mcp
Render LDraw/LEGO models to images with real part geometry via headless Blender + ImportLDraw

phylokit-mcp
Phylogenetic inference via IQ-TREE 3 — never returns a topology without its support

Plant Genomics
Plant genomics MCP — 56 tools across 23 backends with cross-source synthesis.

plantcv-mcp
Plant phenotyping via PlantCV — returns traits plus the segmentation overlay they came from

tmodloader-mcp
Drive a running tModLoader (Terraria) instance from an agent: launch, query, screenshot, read state.