{
  "slug": "io-github-musharna-data-aggregator-mcp",
  "name": "io.github.musharna/data-aggregator-mcp",
  "title": "Data Aggregator",
  "description": "Find & fetch research datasets across 21 archives, omics registries, and literature sources.",
  "version": "0.75.4",
  "publishedAt": "2026-10-20T03:18:39.40633Z",
  "updatedAt": "2026-10-20T03:18:39.40633Z",
  "repoUrl": "https://github.com/musharna/data-aggregator-mcp",
  "websiteUrl": null,
  "namespace": {
    "type": "github",
    "owner": "musharna"
  },
  "kind": "local",
  "packages": [
    {
      "registryType": "pypi",
      "identifier": "data-aggregator-mcp",
      "version": "0.75.4",
      "transport": "stdio",
      "runtimeHint": "uvx"
    }
  ],
  "remotes": [],
  "envVars": [
    {
      "name": "NCBI_API_KEY",
      "isSecret": true,
      "isRequired": false,
      "description": "Optional NCBI E-utilities API key; raises the rate limit 3->10 req/s for omics, literature, and taxonomy lookups."
    },
    {
      "name": "LLM_API_BASE",
      "isSecret": false,
      "isRequired": false,
      "description": "Base URL of an OpenAI-compatible /chat/completions endpoint; enables search(understand=true) and search(multi_query=true)."
    },
    {
      "name": "LLM_API_KEY",
      "isSecret": true,
      "isRequired": false,
      "description": "Bearer token for the LLM endpoint (LLM_API_BASE); omit for keyless local servers."
    },
    {
      "name": "LLM_MODEL",
      "isSecret": false,
      "isRequired": false,
      "description": "Model name passed to the LLM endpoint (default: gpt-4o-mini); set to whatever your endpoint serves."
    },
    {
      "name": "EMBEDDING_API_BASE",
      "isSecret": false,
      "isRequired": false,
      "description": "Base URL of an OpenAI-compatible /embeddings endpoint; enables search(rank=semantic) re-ranking."
    },
    {
      "name": "EMBEDDING_API_KEY",
      "isSecret": true,
      "isRequired": false,
      "description": "Bearer token for the embeddings endpoint (EMBEDDING_API_BASE); omit for keyless local servers."
    },
    {
      "name": "EMBEDDING_MODEL",
      "isSecret": false,
      "isRequired": false,
      "description": "Model name passed to the embeddings endpoint (default: text-embedding-3-small)."
    },
    {
      "name": "DATA_GOV_API_KEY",
      "isSecret": true,
      "isRequired": false,
      "description": "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."
    },
    {
      "name": "UNPAYWALL_EMAIL",
      "isSecret": false,
      "isRequired": false,
      "description": "Email address sent to the Unpaywall API; required to enable the Unpaywall PDF fallback leg of literature full-text retrieval."
    },
    {
      "name": "NCBI_EMAIL",
      "isSecret": false,
      "isRequired": false,
      "description": "Contact address sent to NCBI's ID converter; falls back to UNPAYWALL_EMAIL when unset."
    },
    {
      "name": "DATAVERSE_BASE_URL",
      "isSecret": false,
      "isRequired": false,
      "description": "Resolve Dataverse DOIs against a different installation (default: https://dataverse.harvard.edu)."
    },
    {
      "name": "CACHE_TTL_SECONDS",
      "isSecret": false,
      "isRequired": false,
      "description": "Resolve-cache lifetime in seconds (default: 3600); an unparseable value falls back to the default."
    }
  ],
  "category": "databases",
  "subcategory": "analysis",
  "company": "",
  "categoryAuto": true,
  "checks": [
    {
      "id": "source-linked",
      "label": "Source repository linked",
      "result": "pass",
      "detail": "https://github.com/musharna/data-aggregator-mcp"
    },
    {
      "id": "version-pinned",
      "label": "Version pinned",
      "result": "pass",
      "detail": "Every package has an explicit version"
    },
    {
      "id": "secrets-requested",
      "label": "Secrets requested",
      "result": "warn",
      "detail": "Asks for 4 secrets: NCBI_API_KEY, LLM_API_KEY, EMBEDDING_API_KEY, DATA_GOV_API_KEY"
    },
    {
      "id": "known-registry",
      "label": "Known package registry",
      "result": "pass",
      "detail": "All packages come from npm, PyPI, OCI, NuGet or MCPB"
    },
    {
      "id": "namespace",
      "label": "Namespace ownership",
      "result": "info",
      "detail": "Name verified via GitHub account musharna"
    },
    {
      "id": "meta-text",
      "label": "Registry text aimed at the AI",
      "result": "pass",
      "detail": "Description and settings contain no hidden characters or instructions to the AI"
    },
    {
      "id": "install-scripts",
      "label": "Install scripts",
      "result": "pass",
      "detail": "data-aggregator-mcp 0.75.4 has no setup.py; nothing runs at install"
    },
    {
      "id": "code-flags",
      "label": "Code red flags",
      "result": "pass",
      "detail": "Read 511 files in data-aggregator-mcp 0.75.4: no obfuscation, encoded execution, credential reads or data-collection endpoints found"
    },
    {
      "id": "ai-text",
      "label": "Text aimed at the AI",
      "result": "pass",
      "detail": "No hidden characters or instructions to the AI in 511 files, including comments and the README"
    }
  ],
  "scannedAt": "2026-10-29",
  "level": "Scanned",
  "install": [
    {
      "label": "Claude Desktop (pypi)",
      "kind": "claude_desktop_json",
      "text": "{\n  \"mcpServers\": {\n    \"data-aggregator-mcp\": {\n      \"command\": \"uvx\",\n      \"args\": [\n        \"data-aggregator-mcp==0.75.4\"\n      ]\n    }\n  }\n}"
    }
  ],
  "curated": true,
  "stars": 4,
  "archived": false,
  "pushedAt": "2026-10-29T02:52:25Z",
  "health": {
    "score": 61,
    "parts": {
      "popularity": 0.3154434573067972,
      "activity": 1,
      "issues": null,
      "security": 0.8
    },
    "fail": 0,
    "warn": 1,
    "raw": {
      "stars": 4,
      "forks": 0,
      "downloads": 303,
      "hn": null,
      "issuesOpen": 5,
      "issuesClosed": 4,
      "prsMerged": 336,
      "commits90": 1140,
      "release": "2026-10-20T03:12:17Z",
      "pushed": "2026-10-29T02:52:25Z",
      "growth": null,
      "growthDays": null,
      "archived": false
    },
    "at": "2026-10-31T07:42:38.200Z"
  }
}