Data Aggregator MCP Server

by musharnaio.github.musharna/data-aggregator-mcpv0.69.1

Search and fetch research datasets across Zenodo, DataCite, NCBI and PubMed/OpenAIRE, with DOI deduplication, paper-to-data linking and verified downloads.

4Pythonstdioofficial registry

context tax

queued

security

queued

cold start

queued

freshness

Active2d ago

Install Data Aggregator MCP server

claude mcp add data-aggregator -e NCBI_API_KEY='<ncbi-api-key>' -e LLM_API_KEY='<llm-api-key>' -e EMBEDDING_API_KEY='<embedding-api-key>' -e DATA_GOV_API_KEY='<data-gov-api-key>' -- uvx data-aggregator-mcp

{
  "mcpServers": {
    "data-aggregator": {
      "command": "uvx",
      "args": [
        "data-aggregator-mcp"
      ],
      "env": {
        "NCBI_API_KEY": "<ncbi-api-key>",
        "LLM_API_KEY": "<llm-api-key>",
        "EMBEDDING_API_KEY": "<embedding-api-key>",
        "DATA_GOV_API_KEY": "<data-gov-api-key>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).

{
  "mcpServers": {
    "data-aggregator": {
      "command": "uvx",
      "args": [
        "data-aggregator-mcp"
      ],
      "env": {
        "NCBI_API_KEY": "<ncbi-api-key>",
        "LLM_API_KEY": "<llm-api-key>",
        "EMBEDDING_API_KEY": "<embedding-api-key>",
        "DATA_GOV_API_KEY": "<data-gov-api-key>"
      }
    }
  }
}

Settings → Developer → Edit Config (claude_desktop_config.json), then restart.

{
  "servers": {
    "data-aggregator": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "data-aggregator-mcp"
      ],
      "env": {
        "NCBI_API_KEY": "<ncbi-api-key>",
        "LLM_API_KEY": "<llm-api-key>",
        "EMBEDDING_API_KEY": "<embedding-api-key>",
        "DATA_GOV_API_KEY": "<data-gov-api-key>"
      }
    }
  }
}

Add to .vscode/mcp.json in your workspace.

{
  "mcpServers": {
    "data-aggregator": {
      "command": "uvx",
      "args": [
        "data-aggregator-mcp"
      ],
      "env": {
        "NCBI_API_KEY": "<ncbi-api-key>",
        "LLM_API_KEY": "<llm-api-key>",
        "EMBEDDING_API_KEY": "<embedding-api-key>",
        "DATA_GOV_API_KEY": "<data-gov-api-key>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json.

Configuration

Variable	Required	Secret	Description
NCBI_API_KEY	—	yes	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	—	yes	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	—	yes	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	—	yes	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.

Freshness

Active — last maintenance signal 2d ago. The newest of the signals below sets the band.

Last commit (default branch)
2026-10-08 · 2d ago · GitHub
Latest release
2026-10-08 · 2d ago · GitHub · v0.69.1
Package published
no data · npm/PyPI
Registry entry updated
2026-10-08 · 2d ago · official registry · v0.69.1

FAQ

›How do I install the Data Aggregator MCP server in Claude Code?

Run: claude mcp add data-aggregator -e NCBI_API_KEY='<ncbi-api-key>' -e LLM_API_KEY='<llm-api-key>' -e EMBEDDING_API_KEY='<embedding-api-key>' -e DATA_GOV_API_KEY='<data-gov-api-key>' -- uvx data-aggregator-mcp. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.

›Does Data Aggregator require an API key?

Yes. It expects NCBI_API_KEY, LLM_API_KEY, EMBEDDING_API_KEY, DATA_GOV_API_KEY, of which 4 are secrets.

›Can I use Data Aggregator as a remote (hosted) MCP server?

No hosted endpoint is published; it runs locally over stdio.

›Is Data Aggregator in the official MCP registry?

Yes, as io.github.musharna/data-aggregator-mcp.