@cyanheads/openalex-mcp-server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@@cyanheads/openalex-mcp-serverSearch for papers about climate change from 2020 to 2023"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Public Hosted Server: https://openalex.caseyjhand.com/mcp
Tools
Four tools for querying the OpenAlex academic research catalog:
Tool Name | Description |
| Search, filter, sort, or retrieve by ID across all 8 entity types. |
| Group-by aggregation for trend and distribution analysis. |
| Resolve a name or partial name to an OpenAlex ID via autocomplete. |
| Walk the citation graph one hop from a seed work: cites, cited_by, or related_to. |
openalex_search_entities
Primary discovery and lookup tool. Covers all OpenAlex entity types (works, authors, sources, institutions, topics, keywords, publishers, funders).
Retrieve a single entity by ID (OpenAlex ID, DOI, ORCID, ROR, PMID, PMCID, ISSN)
Keyword search with boolean operators, quoted phrases, wildcards, and fuzzy matching
Exact and AI semantic search modes
Rich filter syntax: AND across fields, OR within fields (
us|gb), NOT (!us), ranges (2020-2024), comparisons (>100)Sensible default field selection per entity type — prevents oversized responses; pass
selectto overrideInvalid
selectfield names produce an error listing the valid fields for that entity typeFormatted MCP output is a generic markdown renderer — every returned field is surfaced without per-entity-type hard-coding
Cursor pagination, sorting, up to 100 results per page
openalex_analyze_trends
Aggregate entities into groups and count them for trend, distribution, and comparative analysis.
Group by any supported field (publication year, OA status, institution, country, topic, etc.)
Combine with filters to scope the population before aggregation
Up to 200 groups per page with cursor pagination
Supports
include_unknownto show entities with no value for the grouped field
openalex_resolve_name
Name-to-ID resolution via autocomplete. Always use this before filtering by entity — names are ambiguous, IDs are not.
Returns up to 10 matches with disambiguation hints
Accepts partial names and DOIs for direct lookup
Optional entity type filter and field-level filters
~200ms response time
openalex_get_citation_graph
One-hop citation graph traversal from a seed work. Wraps the OpenAlex cites/cited_by/related_to filters behind an explicit direction argument so callers do not have to know the filter names.
cites: works that cite the seed (incoming citations)cited_by: works the seed cites (its reference list)related_to: OpenAlex algorithmic "related works" (~8-30 typical, may be empty for less-cited seeds)Accepts OpenAlex IDs, DOIs, PMIDs, PMCIDs as
seed_id; validates the seed via a singleton/works/{id}lookup before walking, so non-existent seeds surface asNotFoundStacks with
filters/sort/selectto narrow the graph (e.g.,publication_year=">2020",is_oa="true")
Prompts
Prompt | Description |
| Guides a systematic literature search: formulate query, search, filter, analyze citation network, synthesize findings. |
| Analyzes the research landscape for a topic: volume trends, top authors/institutions, open access rates, funding sources. |
Features
Built on @cyanheads/mcp-ts-core:
Declarative tool definitions — single file per tool, framework handles registration and validation
Unified error handling across all tools
Pluggable auth (
none,jwt,oauth)Swappable storage backends via the framework (not currently used by this server)
Structured logging with optional OpenTelemetry tracing
Runs locally (stdio/HTTP) or in Docker from the same codebase
OpenAlex-specific:
Typed API client with automatic ID normalization (DOI, ORCID, ROR, PMID, PMCID, ISSN, OpenAlex URLs)
Abstract reconstruction from inverted indices — plaintext instead of OpenAlex's position-keyed encoding
HTTP status codes mapped to specific MCP error classes (400/422 → InvalidParams, 429 → RateLimited, etc.) with upstream messages surfaced
Timeout-aware request retries and cancellation support via
AbortSignal
Getting Started
Public Hosted Instance
A public instance is available at https://openalex.caseyjhand.com/mcp — no installation required. Point any MCP client at it via Streamable HTTP:
{
"mcpServers": {
"openalex-mcp-server": {
"type": "streamable-http",
"url": "https://openalex.caseyjhand.com/mcp"
}
}
}Self-Hosted / Local
Add to your MCP client config (e.g., claude_desktop_config.json):
{
"mcpServers": {
"openalex-mcp-server": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@cyanheads/openalex-mcp-server"],
"env": {
"OPENALEX_API_KEY": "your-email@example.com"
}
}
}
}No API key needed — just provide your email to access the polite pool (10x faster rate limits).
Prerequisites
Bun v1.3.0 or higher (for development)
Installation
Clone the repository:
git clone https://github.com/cyanheads/openalex-mcp-server.gitNavigate into the directory:
cd openalex-mcp-serverInstall dependencies:
bun installConfiguration
Variable | Description | Default |
| Optional. Email address for the OpenAlex polite pool (10x faster rate limits). Without it, anonymous rate limits apply. | — |
| OpenAlex API base URL. |
|
| Transport: |
|
| Port for HTTP server. |
|
| Auth mode: |
|
| Comma-separated allow-list of browser | loopback only |
| Log level (RFC 5424). |
|
| Directory for log files (Node.js only). |
|
| Enable OpenTelemetry instrumentation (spans, metrics, completion logs). |
|
Running the Server
Local Development
Build and run the production version:
bun run build bun run start:http # or start:stdioRun checks and tests:
bun run devcheck # Lints, formats, type-checks bun run test # Runs test suite
Docker
docker build -t openalex-mcp-server .
docker run -e OPENALEX_API_KEY=your-key -p 3010:3010 openalex-mcp-serverProject Structure
Directory | Purpose |
| Tool definitions ( |
| Prompt definitions ( |
| OpenAlex API client service and domain types. |
| Environment variable parsing and validation with Zod. |
| Unit and integration tests, mirroring the |
Development Guide
See CLAUDE.md for development guidelines and architectural rules. The short version:
Handlers throw, framework catches — no
try/catchin tool logicUse
ctx.logfor logging,ctx.statefor storageAlways resolve names to IDs via
openalex_resolve_namebefore using them in filters
Contributing
Issues and pull requests are welcome. Run checks before submitting:
bun run devcheck
bun run testLicense
Apache-2.0 — see LICENSE for details.
This server cannot be installed
Maintenance
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/cyanheads/openalex-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server