scholardata

scholardata is a small local bridge to the hosted HasData Google Scholar MCP server, which returns Google Scholar data as JSON. Ask it a scholarly question and it searches the index for papers, returning each hit with its citation count and versions; hand it the case id from a case-law result and it fetches that opinion in full, parties, court, dates and cited cases included; hand it one search result's id and it returns that result's citation snippets in MLA, APA, Chicago, Harvard and Vancouver, plus the export links for reference managers.

The bridge keeps no scholarly data of its own. It serves the upstream server's tool list locally, exactly as captured from the live endpoint, and forwards each tool call upstream, returning the result untouched. The captured surface is read-only: it searches public bibliographic records and reads public court opinions. There is no write, messaging, or payment tool in it.

Tools

• hasdata_google_scholar_scholar_getScholarSearchResults — search Google Scholar. Required: q (the query, which may use author: and source: helpers). Optional: hl, lr, start and num for paging, asYlo and asYhi for a year range, cites and cluster for cited-by and all-versions lookups, asSdt to scope the search to case law or patents, and the safe, filter, asVis, asRr and scisbd filters. Returns each organic result with title, link, snippet, publication info, cited-by count and link, related-articles link, and all-versions count and link.
• hasdata_google_scholar_case_law_getScholarCaseLawOpinion — fetch one case-law opinion. Required: caseId (as returned in a case-law search result). Optional: hl. Returns the case title, party names, court, procedural history, argued and decided dates, short citations, docket numbers, and every case cited in the opinion.
• hasdata_google_scholar_cite_getScholarCitationFormats — citation formats for one search result. Required: q (the result's resultId). Optional: hl. Returns MLA, APA, Chicago, Harvard and Vancouver snippets and BibTeX, EndNote, RefMan and RefWorks export links.

Configuration

• HASDATA_GOOGLE_SCHOLAR_MCP_URL (optional) — override the upstream endpoint. Defaults to https://mcp.hasdata.com/mcp?apis=google_scholar. (The override hook is this rebuild's own labelled reconstruction.)
• HASDATA_API_KEY (optional) — when set, every upstream request carries an x-api-key: <key> header, for the caller's own HasData API key. When it is not set, no key header is sent. (The header name and the env name are pinned by the original's registry record; forwarding the key from this env var is a labelled reconstruction — the original surface was captured keyless.)

Forwarding mechanics

On the first tool call the client opens a streamable HTTP session with the upstream: a JSON-RPC initialize request (protocolVersion 2025-03-26, clientInfo name scholardata), then a notifications/initialized notification, then the tools/call request carrying the caller's arguments unchanged. When the upstream answers initialize with an Mcp-Session-Id header, that value rides on every later request of the session, which is reused for the life of the process. Replies may arrive as plain JSON or as server-sent events; both are read.

Successful upstream results pass through verbatim, including any isError flag the upstream sets. Failures — a JSON-RPC error, a non-2xx status, an unreadable response, or a request that cannot be completed — come back as an isError result whose text starts with scholardata error: (this rendering is this rebuild's own labelled reconstruction).

CLI

Each tool is also a subcommand taking one JSON argument string:

npx @reneturcios/scholardata hasdata_google_scholar_scholar_getScholarSearchResults '{"q":"attention is all you need","asYlo":2017}'
npx @reneturcios/scholardata hasdata_google_scholar_case_l

... [View full README on GitHub](https://github.com/cloudcorprecords/scholardata#readme)