Connects Claude to Harvard Dataverse's repository of 150,000+ research datasets through a streamable HTTP gateway. You get four tools: search across datasets, files, and collections; fetch dataset metadata by DOI; list files within a dataset; and pull collection metadata by alias or ID. Part of the Pipeworx gateway ecosystem, so you can either connect directly to this single server or use the unified gateway for access to 600+ data sources. Useful when you need programmatic access to academic research data, want to explore interdisciplinary datasets, or need to reference specific DOI-indexed materials without leaving your AI workflow.
Harvard Dataverse MCP.
Part of Pipeworx — an MCP gateway connecting AI agents to 673+ live data sources.
| Tool | Description |
|---|---|
search | Search datasets / files / dataverses. |
dataset | Dataset metadata by DOI persistent id (e.g. "doi:10.7910/DVN/..."). |
dataset_files | List files in a dataset. |
dataverse | Dataverse (collection) metadata by alias or id. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"dataverse-harvard": {
"url": "https://gateway.pipeworx.io/dataverse-harvard/mcp"
}
}
}
Or connect to the full Pipeworx gateway for access to all 673+ data sources:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Instead of calling tools directly, you can ask questions in plain English:
ask_pipeworx({ question: "your question about Dataverse Harvard data" })
The gateway picks the right tool and fills the arguments automatically.
MIT