mcp-openalex
Enables fetching work metadata by DOI.
Supports Elasticsearch syntax for advanced work queries via OpenAlex.
Allows searching and fetching authors by ORCID.
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., "@mcp-openalexsearch for papers on transformer models published in 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.
mcp-openalex
MCP server for the OpenAlex scholarly database. Gives AI agents tools to search and retrieve academic works, authors, and institutions.
Requirements
Python >= 3.12
OpenAlex API key (get one for free)
Related MCP server: scholar-mcp
Installation
git clone https://github.com/ELumya/openalex-mcp.git
cd openalex-mcp
uv syncConfiguration
Copy the example env file and set your API key:
cp .env.example .env
# edit .env and set OPENALEX_API_KEY=your-key-hereRunning
STDIO (default — for local MCP clients):
uv run fastmcp run src/server.pyHTTP transport:
MCP_TRANSPORT=http MCP_HOST=127.0.0.1 MCP_PORT=8000 uv run fastmcp run src/server.pyMCP Tools
Tool | Description |
| Search works with filters (institution, year, date range, type, peer-reviewed) |
| Find works similar to a text using AI semantic search (matches by meaning) |
| Fetch full work metadata by OpenAlex ID or DOI — optionally extract PDF or request an LLM summary |
| Search author profiles by name or ORCID |
| Fetch full author profile by OpenAlex ID or ORCID |
| List all publications by a specific author |
| Search institutions by name, country, or type |
| Fetch full institution profile by OpenAlex ID or ROR |
Architecture
See ARCHITECTURE.md for system overview, module dependency graph, and tool flow diagrams.
TODOs
Add tests
Add CI/CD
Use cache for high rate requests
Scan code base for dead code
Add mermaid documentation
Unify concepts names (ie. Articles/Works)
Two levels of formating details in
filter: low (current one), medium (forfetch_*tools)
Tools Evolutions
Test OpenAlex support of Elasticsearch: YES!
Update work search tools descriptions, add: "Elasticsearch syntax"
Update tools descriptions, do not explain how it works but what you need to pass.
Update Author search tool, remove IDs handling (use
fetch_authorfor this)
in format_work_result add:
first 3 Authors
Primary topic classification
in _process_fulltext in fetch_work
Remove pure PDF handling, auto-detect format based on prompt presence (if prompt provided → LLM summary, else → markdown)
Use proper sampling parameters
Search
Semantic search, added as a new tool but can easily be integrated to work_search, we perform modifications at filters
build_works_query.Search by topics
Search foundational works
Citation
graph_work_citations
Authors
get_author_works: parameter
authorreplaced byauthor_id; accepts only OpenAlex ID or ORCID.graph_collaborations
Institutions
graph_colaborations
Global analysis tools
OpenAlex Topic comparaison
Geographical Region comparaison
Institutions comparaison
Trend deep analysis
License
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
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/ELumya/openalex-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server