About orcid
An MCP server for researchers and literature workflows, enabling ORCID registry search, profile and publication retrieval, and citation export in RIS or BibTeX.
Key features
- 01Search researchers by name, affiliation, keyword, DOI, or Solr query
- 02Read profile, employment, education, and keywords
- 03Retrieve publications from ORCID records
- 04Export works as RIS or BibTeX
Use cases
- 01Find researchers by institution or research topic
- 02Review an ORCID profile and its publications
- 03Prepare citations for Zotero or EndNote
MCP support
Exposes ORCID search, profile, works, and citation-export tools to MCP clients, using the ORCID Public API v3.0.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
uvx orcid-mcp-serverORCID_CLIENT_IDSecretORCID API client ID from https://orcid.org/developer-toolsORCID_CLIENT_SECRETSecretORCID API client secretLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEORCID MCP Server
An MCP (Model Context Protocol) server that provides tools for searching the ORCID registry, reading researcher profiles, retrieving publications, and exporting citations in RIS and BibTeX formats.
Built with FastMCP and the ORCID Public API v3.0.
Tools
| Tool | Description |
|---|---|
orcid_search | Search for researchers by name, affiliation, keyword, DOI, or advanced Solr query |
orcid_read_record | Read a researcher's full profile (bio, employment, education, keywords) |
orcid_read_works | Get publications from a researcher's ORCID record |
orcid_export_ris | Export retrieved works as RIS (for Zotero, EndNote, etc.) |
orcid_export_bibtex | Export retrieved works as BibTeX |
Setup
1. Get ORCID API credentials
Register for free public API credentials at ORCID Developer Tools.
2. Install
cd orcid-mcp-server
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
3. Configure environment
Copy the example env file and add your credentials:
cp .env.example .env
# Edit .env with your ORCID_CLIENT_ID and ORCID_CLIENT_SECRET
4. Add to Claude Desktop
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"orcid-mcp": {
"command": "/path/to/orcid-mcp-server/venv/bin/python",
"args": ["/path/to/orcid-mcp-server/server.py"],
"env": {
"ORCID_CLIENT_ID": "your-client-id",
"ORCID_CLIENT_SECRET": "your-client-secret"
}
}
}
}
Or if using Claude Code CLI:
claude mcp add orcid-mcp \
/path/to/orcid-mcp-server/venv/bin/python \
/path/to/orcid-mcp-server/server.py \
-e ORCID_CLIENT_ID=your-client-id \
-e ORCID_CLIENT_SECRET=your-client-secret
Usage examples
Once connected, you can ask Claude things like:
- "Search ORCID for researchers at Northwestern University working on machine learning"
- "Look up the ORCID profile for 0000-0002-1825-0097"
- "Get the publications for this researcher and export them as RIS for Zotero"
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.