Skip to main content
Glama
Sign In
openalex-mcp

openalex-mcp

by ckgerteis
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

oa_search_works

Read-onlyIdempotent

Search OpenAlex for scholarly works—articles, books, datasets, and theses—and narrow results by year, author, institution, source, or open-access status.

Instructions

Search OpenAlex for scholarly works (articles, books, datasets, theses). Returns the unified envelope.

OpenAlex matches title, abstract and indexed full text with stemming, so result.total is a loose count (matching_mode full_text_stemmed) and a high breadth is expected. Titles are typed by OpenAlex's own language field; where that is absent, a CJK title is kept only in extra.title rather than guessed into ja or ko. Filters by year, author, institution, source and open-access status narrow the set exactly. OpenAlex charges per call, not per result: a sweep that pages through results should set per_page 200.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "params": "<params>"
    },
    "name": "oa_search_works"
  }
}

Input Schema

NameRequiredDescriptionDefault
paramsYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.3.0
    • changedInput schema / $defs / WorkSearchInput / properties / per_page / description
      Previous value: -"Results per page (1-200)"New value: +"Results per page (1-200). OpenAlex charges per call, not per result, so a sweep that will page through results should set 200."
  2. Changed1 schema field changedv2.2.0
    • addedInput schema / $defs / WorkSearchInput / properties / query / maxLength
      Added value: +2000
  3. First observedv1.1.0

TDQS

A4.5/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description goes well past them: stemming means total is a loose count, CJK titles fall back to extra.title rather than a guessed language, and billing is per call so page size should be maximized. That is exactly the non-obvious behavior an agent needs before issuing a query.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four compact sentences, each adding a distinct fact, with the core purpose front-loaded. 'Returns the unified envelope' is a slightly opaque phrase, but the output schema covers the return shape.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a search tool with an output schema and rich annotations, the description supplies the missing pieces: matching behavior, count reliability, language handling, and cost-aware paging. Only sorting behavior and pagination limits are left unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With near-zero effective schema coverage, the description carries the weight and names the filter dimensions (year, author, institution, source, open-access) and the per_page trade-off. It leaves sort_by values and page semantics to the schema, so it is strong but not exhaustive.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb and resource ('Search OpenAlex for scholarly works') and enumerates the covered record types (articles, books, datasets, theses). The name plus this sentence makes it unambiguously distinct from oa_search_authors, oa_search_sources, and oa_search_institutions without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives actionable context: filters narrow exactly, broad queries produce high result.total because of stemming, and a paging sweep should set per_page 200. It does not explicitly say when to prefer oa_cited_by, oa_author_works, or oa_get_work instead, so alternative routing is left implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools