dataverse-harvard 4 tools

MCP server exposing 4 tools for dataverse-harvard.

Endpoint

This URL is a JSON-RPC 2.0 endpoint over HTTP. Issue POST requests with a JSON-RPC body. Browsers and search crawlers land here on GET.

POST https://gateway.pipeworx.io/dataverse-harvard/mcp
Content-Type: application/json

{"jsonrpc":"2.0","id":1,"method":"tools/list"}

search — Keyword search across Harvard Dataverse — the ~200k-dataset open research repository. Returns dataset titles, DOIs, authors, publication dates and descriptions; pass a returned DOI to dataset or dataset_files. Use to find research data behind a paper or topic (e.g. "climate", "survey experiment", "replication data").
dataset — Full metadata for one Harvard Dataverse dataset by its DOI persistent id: title, authors, abstract, subject, keywords, version and publication date. The id must come from search — DOIs cannot be guessed.
dataset_files — List all files in the latest version of a Harvard Dataverse dataset identified by its DOI persistent ID (e.g. "doi:10.7910/DVN/..."), returning file names, content types, sizes, and download URLs. For files Dataverse has TABULAR-INGESTED (CSV/DTA/SAV/POR under its ingest size limit), also returns exact COLUMN / VARIABLE NAMES and labels from Dataverse's DDI metadata (variables_by_file). If a dataset has no tabular-ingested files (common for very large files, or non-tabular formats), column names are not available from Dataverse at all — the response says so explicitly rather than silently omitting them.
dataverse — Dataverse (collection) metadata by alias or id.

Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/dataverse-harvard/

Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io