Data Aggregator

Package (pypi 0.75.4)

uvx data-aggregator-mcp

Or add to your MCP client config:

{
  "mcpServers": {
    "data-aggregator-mcp": {
      "command": "uvx",
      "args": [
        "data-aggregator-mcp"
      ],
      "env": {
        "NCBI_API_KEY": "<YOUR_VALUE>",
        "LLM_API_KEY": "<YOUR_VALUE>",
        "EMBEDDING_API_KEY": "<YOUR_VALUE>",
        "DATA_GOV_API_KEY": "<YOUR_VALUE>"
      }
    }
  }
}

• NCBI_API_KEY secret — 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_KEY secret — 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_KEY secret — 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_KEY secret — 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.