Skip to content
mcp/harbor
Grok

Data Aggregator for Grok

io.github.musharna/data-aggregator-mcp

Find & fetch research datasets across 17 archives, omics registries, and literature sources.

client:Grok transport:stdio runtime:pypi

Install Data Aggregator in Grok

.mcp.json (in your project root)

Held in this page only — never stored, logged, or sent anywhere but back to your screen. 

{
  "mcpServers": {
    "data-aggregator-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "data-aggregator-mcp"
      ],
      "env": {
        "NCBI_API_KEY": "<NCBI_API_KEY>",
        "LLM_API_BASE": "<LLM_API_BASE>",
        "LLM_API_KEY": "<LLM_API_KEY>",
        "LLM_MODEL": "<LLM_MODEL>",
        "EMBEDDING_API_BASE": "<EMBEDDING_API_BASE>",
        "EMBEDDING_API_KEY": "<EMBEDDING_API_KEY>",
        "EMBEDDING_MODEL": "<EMBEDDING_MODEL>",
        "DATA_GOV_API_KEY": "<DATA_GOV_API_KEY>",
        "UNPAYWALL_EMAIL": "<UNPAYWALL_EMAIL>",
        "NCBI_EMAIL": "<NCBI_EMAIL>",
        "DATAVERSE_BASE_URL": "<DATAVERSE_BASE_URL>",
        "CACHE_TTL_SECONDS": "<CACHE_TTL_SECONDS>"
      }
    }
  }
}

Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs

Data Aggregator in other clients

Data Aggregator MCP server