{
  "markdown": "# Crossref — DOI Metadata\n\nCrossref is the largest DOI (Digital Object Identifier) registration agency. Every DOI you've seen in an academic citation goes through them. Their API exposes structured metadata for ~150M+ scholarly works: titles, authors, ORCIDs, abstracts where available, references, citation graphs. Free, no auth required.\n\nPart of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1476+ live data sources.\n\n## Why this matters for AI agents\n\nWhere [Semantic Scholar](/docs/reference/semantic-scholar) is search-focused, Crossref is the authoritative source for *DOI metadata*. If you have a DOI and need its canonical metadata, Crossref is the answer. Citation networks are also more complete here than in many discipline-specific databases.\n\nCommon flows:\n\n- **DOI → metadata.** `crossref_get_work({doi: \"10.48550/arXiv.1706.03762\"})` → title, authors, journal, year, citations.\n- **Author DOIs.** Find a researcher's published works by ORCID or name.\n- **Citation graph.** A paper's references and which papers cite it (where reported).\n\nFor free-text academic search, prefer [Semantic Scholar](/docs/reference/semantic-scholar) — Crossref's search is more limited.\n\nCitable URI: `pipeworx://crossref/work/{doi}`.\n\n## Auth\n\nPublic, free. Crossref has a \"polite pool\" giving priority to clients that identify themselves via User-Agent. Pipeworx forwards `pipeworx-mcp/1.0 (https://pipeworx.io)` so we get polite-pool treatment by default.\n\n## What's in a Crossref record\n\n| Field | Notes |\n|---|---|\n| Title | Authoritative |\n| Authors with ORCID | When the publisher recorded ORCIDs |\n| Journal / publisher / year | Stable identifiers |\n| References (the cited works) | Coverage varies by publisher |\n| References by (citers) | Available via separate \"is-referenced-by-count\" |\n| Open-access link | When publisher provides it |\n| Funder data | NSF, NIH, etc. when reported |\n\n## Common pitfalls\n\n- **Reference-list completeness.** Some publishers send their full reference list to Crossref; others don't. A paper with 0 references in Crossref may have 50 in print. For exhaustive citation graphs, cross-reference with Semantic Scholar.\n- **Errata and retractions.** Crossref tracks \"scholix\" links between original and retraction notices. Always check the `relation` field for `is-retracted-by` before citing.\n- **Author ORCID coverage.** ORCID adoption has grown but isn't universal. Older papers and small-publisher works often lack ORCIDs. Don't rely on ORCID-based deduplication for full coverage.\n- **DOI normalization.** Different sources format DOIs slightly differently: `10.1234/xyz`, `https://doi.org/10.1234/xyz`, `doi:10.1234/xyz`. Crossref accepts the bare form. Strip prefixes before passing to the API.\n- **Books and chapters.** Crossref covers books and chapters as well as articles. The `type` field tells you which (`journal-article`, `book-chapter`, `proceedings-article`, etc.). For systematic literature reviews, type filtering matters.\n- **Pre-prints.** Some pre-print servers register DOIs through Crossref (arXiv, bioRxiv). The same content may have multiple DOIs (pre-print + accepted version). Track via `relation` field.\n\n## Quick Start\n\nAdd to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):\n\n```json\n{\n  \"mcpServers\": {\n    \"crossref\": {\n      \"url\": \"https://gateway.pipeworx.io/crossref/mcp\"\n    }\n  }\n}\n```\n\n### What this endpoint actually serves\n\n`tools/list` at `https://gateway.pipeworx.io/crossref/mcp` returns the tools in the table\nabove **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,\n`discover_tools`, `search_within`, `remember`/`recall` and the rest of the\ngateway-wide set. So the tool count you see is larger than this table: a\nsingle-pack endpoint currently lists roughly 30 shared tools alongside the\npack's own. The connection's `initialize` response states its exact scope, and\nis the authoritative answer for a given day.\n\nThis is deliberate, not multiplexing by accident. The meta-tools are what let a\nscoped connection answer a question this pack does not cover — via\n`ask_pipeworx`, which routes across the whole catalog — without you adding a\nsecond MCP server. There is currently no way to mount a pack endpoint without\nthem; if the extra schemas cost you more context than the routing is worth,\nconnect to the full gateway once rather than to several pack endpoints.\n\nOr connect to the full Pipeworx gateway to get every pack's tools listed\ndirectly, instead of just this one's:\n\n```json\n{\n  \"mcpServers\": {\n    \"pipeworx\": {\n      \"url\": \"https://gateway.pipeworx.io/mcp\"\n    }\n  }\n}\n```\n\nBoth URLs reach the same gateway and the same 1476+ data sources. The\nonly difference is which pack's tools are listed **directly**; `ask_pipeworx`\nreaches all of them from either one.\n\n## Using with ask_pipeworx\n\nInstead of calling tools directly, you can ask questions in plain English —\nthis works on the pack endpoint above as well as on the full gateway:\n\n```\nask_pipeworx({ question: \"your question about Crossref data\" })\n```\n\nThe gateway picks the right tool and fills the arguments automatically.\n\n## More\n\n- [Docs and guides](https://pipeworx.io/docs)\n- [pipeworx.io](https://pipeworx.io)\n\n## License\n\nMIT\n",
  "bytes": 5224,
  "sha": "16843b248e1f21d3e9570b042039720c30a8b6f4511f031bbf47beaa3f65ed26",
  "repo_slug": "pipeworx-io/mcp-crossref",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_pipeworx_io_crossref_575de683/readme"
}