Orcid MCP Server

Orcid MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Search ORCID researcher profiles, retrieve works, and export citations.

What you get

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.

Setting it up

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

What the assistant can call

Once Orcid is connected, these are the calls the assistant has available:

• 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

Configuration and credentials

You will need 2 environment variables: ORCID_CLIENT_ID, ORCID_CLIENT_SECRET. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Before you rely on it

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the orcid mcp server does with a few real requests.

Choosing this one

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Orcid's toolset — orcid_search, orcid_read_record, orcid_read_works and 2 more — is a fair guide to whether it matches your workflow. It is maintained by SMABoundless; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.