Crossref

Crossref — DOI Metadata

Crossref 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.

Part of Pipeworx — an MCP gateway connecting AI agents to 1854+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Why this matters for AI agents

Where 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.

Common flows:

• DOI → metadata. crossref_get_work({doi: "10.48550/arXiv.1706.03762"}) → title, authors, journal, year, citations.
• Author DOIs. Find a researcher's published works by ORCID or name.
• Citation graph. A paper's references and which papers cite it (where reported).

For free-text academic search, prefer Semantic Scholar — Crossref's search is more limited.

Citable URI: pipeworx://crossref/work/{doi}.

Auth

Public, 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.

What's in a Crossref record

Common pitfalls

• 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.
• Errata and retractions. Crossref tracks "scholix" links between original and retraction notices. Always check the relation field for is-retracted-by before citing.
• 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.
• 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.
• 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.
• 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.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "crossref": {
      "url": "https://gateway.pipeworx.io/crossref/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/crossref/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1854+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/crossref_search_works \
  -H 'Content-Type: application/json' \
  -d '{"query":"climate change machine learning"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/crossref_search_works. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "crossref": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-crossref"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-crossref

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Crossref data" })

The gateway picks the right tool and fills the arguments automatically.

More

• Docs and guides
• pipeworx.io

License

MIT