Hitting all four indexes in parallel is what makes this worth a tool call instead of a browser tab: preprints on arXiv, conference records in DBLP, and the wider coverage of Semantic Scholar and OpenAlex resolve together. The hosted endpoint needs no account, and the only key involved is optional and buys you throughput, not access.
A reference-search server that queries arXiv, DBLP, Semantic Scholar and OpenAlex concurrently and generates BibTeX from what it finds. There is a public hosted endpoint, so trying it costs nothing more than adding a URL.
- One search across arXiv, DBLP, Semantic Scholar and OpenAlex, run in parallel rather than one after another
- BibTeX generation for the matches, ready to drop into a bibliography
- A hosted endpoint at https://mcp.florianbrand.de/sse over SSE, with no authentication required
- The same code runs locally when you would rather not send queries to someone else's host
Nothing for the hosted path — point your client at the SSE URL exactly as written, without a www subdomain. To run it yourself, the Python package is `reference-mcp`, version 0.1.0, launched with `uv run --directory <path> python -m reference_mcp --stdio`. A Semantic Scholar API key in `SEMANTIC_SCHOLAR_API_KEY` is optional and raises your rate limit.
One command — uvx reference-mcp