OpenAlex — Open Catalog of Scholarly Works

OpenAlex is a free, open replacement for Microsoft Academic Graph (which shut down in 2022). 240M+ scholarly works with structured data on authors, institutions, concepts, citations, and venues. Open-source data model, generous API. Free, no auth (polite User-Agent + email recommended).

Part of Pipeworx — an MCP gateway connecting AI agents to 1394+ live data sources.

Why this matters for AI agents

Where Semantic Scholar is search-focused and Crossref is DOI-focused, OpenAlex is the most comprehensive structured graph: papers + authors + institutions + funders + concepts, all linked. For institutional analysis, citation networks, or systematic literature review, OpenAlex covers ground the others don't.

Common flows:

• Work lookup. Find a paper by DOI, title, or OpenAlex ID; get full structured record.

• Author / institution. Search Yale's CS department's papers in 2024.

• Concept browsing. Papers tagged with "transformer architecture" or "CRISPR Cas9."

• Citation graph. "Who cites paper X?" or "What does paper X cite?"

Citable URI: pipeworx://openalex/work/{work_id}.

Related MCP server: mcp-semanticscholar

Auth

Free, public. OpenAlex strongly encourages identifying yourself via mailto= query parameter or User-Agent for "polite pool" priority. Pipeworx forwards mailto=support@pipeworx.io and User-Agent: Pipeworx (mailto:support@pipeworx.io) automatically.

Entity types

OpenAlex models 5 entity types, each with stable IDs:

Works are linked to authors, institutions (where authors are affiliated), venues (where they were published), and concepts (what they're about). Cross-entity queries are powerful.

Common pitfalls

• Author disambiguation. OpenAlex makes a serious effort but isn't perfect. The same person may have separate Author IDs across early-career vs late-career; common-name authors split across entities. Cross-reference with ORCID where available.

• Concept hierarchy depth. OpenAlex concepts form a 6-level tree. "Computer science" level 0 is too coarse for most queries; level 3-4 ("transformer model", "BERT model") is more useful.

• Open access status. OpenAlex tracks oa_status (gold, green, hybrid, bronze, closed). Use it to surface free-to-read versions in your output.

• Citation count vs. cited-by. OpenAlex computes citation counts from its own corpus. Same paper can show different counts in Google Scholar (broader) and Web of Science (narrower).

• Lag. New papers appear within weeks. Citations to those papers take longer because citing papers must themselves be indexed.

• Tied to Semantic Scholar? OpenAlex and Semantic Scholar are separate projects with separate data. Some overlap in coverage; some divergence in metadata. Use both for comprehensive lookups.

Quick Start

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

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

Or connect to the full Pipeworx gateway for access to all 1394+ data sources:

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

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English:

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

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

More

• Docs and guides

• pipeworx.io

License

MIT