加载中…
Find & fetch research datasets across 21 archives, omics registries, and literature sources.
Data Aggregator 是 ChatHome Skills 收录的 MCP 条目，来源为 Official MCP Registry，质量分 78/100。 作为 Model Context Protocol 服务器，它向 Claude、Cursor、Copilot 等兼容 MCP 的 LLM 客户端暴露可直接调用的工具，让 agent 的能力超出模型内置范围。 该条目由 ChatHome Skills 的每日抓取从官方 registry 和 GitHub 发现查询中收录，每次运行都会重新核验仓库事实、新鲜度信号和安装元数据。 质量分综合了官方 registry 收录情况、可用安装命令、许可证完整性、仓库活跃度和 GitHub star 趋势，完整算法说明见来源页。安装命令已列于上方，可直接复制使用。 在将 Data Aggregator 加入生产 agent 工作流前，请核对上方的最近更新日期和仓库状态——下方事实快照是最近一次抓取的时点值。
uvx data-aggregator-mcp==0.75.4运行此命令前，请先核对上游源码。
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-10-20T03:18:39.40633Z",
"publishedAt": "2026-10-20T03:18:39.40633Z",
"statusChangedAt": "2026-10-20T03:18:39.40633Z"
}
},
"server": {
"name": "io.github.musharna/data-aggregator-mcp",
"title": "Data Aggregator",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "0.75.4",
"packages": [
{
"version": "0.75.4",
"transport": {
"type": "stdio"
},
"identifier": "data-aggregator-mcp",
"runtimeHint": "uvx",
"registryType": "pypi",
"registryBaseUrl": "https://pypi.org",
"environmentVariables": [
{
"name": "NCBI_API_KEY",
"isSecret": true,
"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",
"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,
"description": "Bearer token for the LLM endpoint (LLM_API_BASE); omit for keyless local servers."
},
{
"name": "LLM_MODEL",
"description": "Model name passed to the LLM endpoint (default: gpt-4o-mini); set to whatever your endpoint serves."
},
{
"name": "EMBEDDING_API_BASE",
"description": "Base URL of an OpenAI-compatible /embeddings endpoint; enables search(rank=semantic) re-ranking."
},
{
"name": "EMBEDDING_API_KEY",
"isSecret": true,
"description": "Bearer token for the embeddings endpoint (EMBEDDING_API_BASE); omit for keyless local servers."
},
{
"name": "EMBEDDING_MODEL",
"description": "Model name passed to the embeddings endpoint (default: text-embedding-3-small)."
},
{
"name": "DATA_GOV_API_KEY",
"isSecret": true,
"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",
"description": "Email address sent to the Unpaywall API; required to enable the Unpaywall PDF fallback leg of literature full-text retrieval."
},
{
"name": "NCBI_EMAIL",
"description": "Contact address sent to NCBI's ID converter; falls back to UNPAYWALL_EMAIL when unset."
},
{
"name": "DATAVERSE_BASE_URL",
"description": "Resolve Dataverse DOIs against a different installation (default: https://dataverse.harvard.edu)."
},
{
"name": "CACHE_TTL_SECONDS",
"description": "Resolve-cache lifetime in seconds (default: 3600); an unparseable value falls back to the default."
}
]
}
],
"repository": {
"url": "https://github.com/musharna/data-aggregator-mcp",
"source": "github"
},
"description": "Find & fetch research datasets across 21 archives, omics registries, and literature sources."
}
}