HasData Google Scholar — Claude Code MCP server: search papers
A hosted MCP server that adds two Google Scholar tools to your agent: literature search and ready-made citations as JSON. No hosting, just a HasData key.
claude mcp add google-scholar -e HASDATA_API_KEY=<HASDATA_API_KEY> -- npx -y @hasdata/google-scholar-mcpWhat HasData Google Scholar does
Two tools sit behind one remote endpoint. The search tool returns each result with its title, link, snippet, authors and their profile links, a cited-by count and the number of indexed versions. The citation tool hands back a formatted reference in five styles — MLA, APA, Chicago, Harvard, Vancouver — along with export URLs for BibTeX, EndNote, RefMan and RefWorks.
Nothing runs on your machine. The transport is streamable HTTP at https://mcp.hasdata.com/mcp?apis=google_scholar, and the x-api-key header carries auth. Clients that only speak stdio go through a launcher published on npm as @hasdata/google-scholar-mcp and on PyPI as hasdata-google-scholar-mcp.
Register a HasData account to get the key; no card is needed for the free tier. Without a valid HASDATA_API_KEY in the environment or the header, calls fail, so wire the key in first. Each successful call costs 10 credits, and the monthly free allowance works out to about 100 calls.
Asking about one paper takes two calls: a search to reach its resultId, then the citation lookup. A question about citing works also takes two, since the second call reuses citedBy.citesId.
What it helps with
- find papers on a topic within a year range, sorted by citation count
- grab a BibTeX or EndNote link for a paper the agent found
- trace which works cite a paper and how that count moved year by year
- get an APA or MLA reference written straight into the agent's answer
- exclude reviews and records without full text from a literature search
Example prompts for the agent
- Find papers on transformer architectures since 2023, sorted by citation count
- Give me the BibTeX for this paper
- Who cited this work, and how did the count change by year?
How to install HasData Google Scholar
1Platform CLI
claude mcp add google-scholar -e HASDATA_API_KEY=<HASDATA_API_KEY> -- npx -y @hasdata/google-scholar-mcpReplace <…> with your own values
2Platform CLI: remote server
claude mcp add --transport http hasdata-google-scholar 'https://mcp.hasdata.com/mcp?apis=google_scholar'1Platform CLI: remote server
codex mcp add hasdata-google-scholar --url 'https://mcp.hasdata.com/mcp?apis=google_scholar'2Platform CLI
codex mcp add hasdata-google-scholar --env HASDATA_API_KEY=<HASDATA_API_KEY> -- npx -y @hasdata/google-scholar-mcpReplace <…> with your own values
Config file
{
"mcpServers": {
"hasdata-google-scholar": {
"url": "https://mcp.hasdata.com/mcp?apis=google_scholar"
}
}
}{
"mcpServers": {
"hasdata-google-scholar": {
"command": "npx",
"args": [
"-y",
"@hasdata/google-scholar-mcp"
],
"env": {
"HASDATA_API_KEY": "<HASDATA_API_KEY>"
}
}
}
}Replace <…> with your own values
Config file
{
"servers": {
"hasdata-google-scholar": {
"type": "http",
"url": "https://mcp.hasdata.com/mcp?apis=google_scholar"
}
}
}{
"servers": {
"hasdata-google-scholar": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@hasdata/google-scholar-mcp"
],
"env": {
"HASDATA_API_KEY": "<HASDATA_API_KEY>"
}
}
}
}Replace <…> with your own values
1Platform CLI: remote server
gemini mcp add -t http hasdata-google-scholar 'https://mcp.hasdata.com/mcp?apis=google_scholar'2Platform CLI
gemini mcp add -e HASDATA_API_KEY=<HASDATA_API_KEY> hasdata-google-scholar npx -y @hasdata/google-scholar-mcpReplace <…> with your own values
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about HasData Google Scholar
How do I install HasData Google Scholar in Claude Code?
Run claude mcp add --transport http hasdata-google-scholar 'https://mcp.hasdata.com/mcp?apis=google_scholar' to register the remote server. The x-api-key header in your client config supplies the key.
What does HasData Google Scholar do?
It queries Google Scholar and returns structured JSON for each hit: authors, cited-by count, all-versions link. A second tool produces a formatted citation in five styles plus BibTeX and EndNote export links.
What do I need for it to work?
A HasData API key, passed either as the x-api-key header or as HASDATA_API_KEY when you run the stdio launcher. Calls cost 10 credits each, and the free tier covers roughly 100 calls a month.
