Skip to main content
Glama
oksure

OpenAlex Research MCP Server

by oksure

search_works

Search scholarly works with Boolean operators, year ranges, citation thresholds, venue/journal filters, and institution filters. Supports exact phrase matching and field-specific searches for precise results.

Instructions

Search scholarly works with advanced filtering. Supports Boolean operators, year ranges, citation thresholds, venue/journal filtering (source_name, source_issn, source_id), and institution filtering (author_institution, institution_group). The most flexible search tool. Use search_in_journal_list for preset journal lists like UTD24 or FT50.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryNoSearch query. Supports Boolean operators (AND, OR, NOT). Example: "machine learning AND (neural networks OR deep learning)". For exact phrase matching (e.g., 'privacy paradox' as a specific concept), set exact_phrase to true.
exact_phraseNoSet to true for exact phrase matching. Without this, search terms are matched independently. Use this when searching for a specific concept or multi-word term (e.g., 'privacy paradox', 'supply chain resilience').
search_fieldNoRestrict search to a specific field: 'title' (paper titles only), 'abstract' (abstracts only), or 'fulltext' (full text only). By default, searches across all fields. Cannot be combined with exact_phrase.
from_yearNoFilter works published from this year onwards
to_yearNoFilter works published up to this year
min_citationsNoMinimum citation count. E.g., 50 for solid papers, 200 for highly influential.
cited_by_countNoCitation filter with operator: ">100", "<50". Prefer min_citations for simplicity.
source_nameNoFilter by journal/conference name (partial match). E.g., "Nature", "NeurIPS", "Management Science".
source_idNoFilter by exact OpenAlex source ID (most reliable for conferences).
source_issnNoFilter by journal ISSN. E.g., "0025-1909" for Management Science.
author_institutionNoFilter by author institution (OpenAlex display_name). Use | for OR. E.g., "Harvard University|Stanford University|MIT".
institution_groupNoNamed institution group preset. Use list_journal_presets to see all. E.g., harvard_stanford_mit, ivy_league, top_us, insead_london, top_global_business.
is_oaNoFilter for open access works only
typeNoFilter by work type: article, review, book-chapter, dataset, etc.
sortNoSort: relevance_score (default), cited_by_count:desc, publication_year:desc
pageNoPage number for pagination (default: 1)
per_pageNoResults per page, max 200 (default: 10; use 20 for broader coverage)
Behavior4/5

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

No annotations were provided, so the description carries the full burden. It discloses advanced filtering capabilities (Boolean operators, exact phrase, field restriction, etc.) and gives examples. However, it does not mention what the response contains (e.g., list of works with metadata) or any limits like pagination maximum beyond per_page max 200.

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

Conciseness5/5

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

The two-sentence description is concise and front-loaded: the first sentence states the purpose, and the second provides usage guidance with a specific sibling tool reference. Every sentence serves a purpose without extraneous information.

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?

Given the complexity (17 parameters, no output schema, no annotations), the description covers the essential aspects: purpose, filtering capabilities, and alternative tool usage. It lacks details about the output structure but is otherwise sufficient for a search tool.

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?

Schema description coverage is 100%, providing a baseline of 3. The description adds value beyond the schema by explaining Boolean operator support, recommending min_citations over cited_by_count, and giving examples for institution filtering. This extra context justifies a score above baseline.

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?

The description clearly states the tool's purpose: 'Search scholarly works with advanced filtering.' It lists many filter types (Boolean operators, year ranges, citation thresholds, venue, institution) and explicitly distinguishes itself from sibling tool 'search_in_journal_list' by noting that the latter is for preset journal lists like UTD24 or FT50.

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

Usage Guidelines5/5

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

The description provides explicit guidance on when to use this tool vs. alternatives: 'The most flexible search tool. Use search_in_journal_list for preset journal lists like UTD24 or FT50.' Also includes recommendations like 'Prefer min_citations for simplicity' for parameter usage.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/oksure/openalex-research-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server