Dear openEHR community, I would like to announce an open-source Model Context Protocol (MCP) server for openEHR that I developed as part of my learning journey at @Sidharth_Ramesh 's excellent openEHR bootcamp: [image] GitHub - deak-ai/openehr-mcp-server Contribute to deak-ai/o…

In our approach to generate examples programmatically we use constructors for different RM types that consider the OPT constraints for that object. Then with the RM instance generated we just use a serializer to get the final format. I think if Claude, instead of generating the final resource, it c…

I would always prefer canonical JSON. LLMs are great with JSON. It would be interesting to test the same MCP server with canonical JSON. We might be surprised that it works even better. @odeak Nice work. The best part is that you did it during a bootcamp :clap: @Sidharth_Ramesh must have a great…

Thanks for the feedback, Ian, adding terminology support to the list!

Thank you for the ideas and links, @pablo , I will need to dig a bit deeper. Related to this I have looking at other LLMs on the list, especially smaller ones that can run locally, which brings additional complexities such as ensuring structured outputs, fine-tuning on RM etc. as well as infrastruct…

Thanks for the suggestion @borut.jures , this could be done as a configuration setting to the MCP server to use flat vs canonical (JSON only for now).

I think if you feed the RM class model implementation to the LLM-MCP (for instance openEHR-SDK/src/main/groovy/com/cabolabs/openehr/rm_1_0_2 at master · CaboLabs/openEHR-SDK · GitHub ), the model will be able to create valid instances of the openEHR RM. Though the difficult part would be to feed the…

Hi @odeak , just wanted to thank you for sharing, it always makes my day when people are building cool stuff on openEHR and EHRbase :slight_smile:

Excellent to see this here @odeak ! I was watching this video, and it reminded me of your work: [Your API is not an MCP | DEMFP786] You’ve done really well to abstract away “actions” from just the usual openEHR REST API. I think this pattern works really well with MCP-like protocols. A…

The flats are short term easy, but the moment you want to apply that to other use-cases other languages they become a problem, since the output fields result out of the template names which users change. So in your domain easy, the moment you want to transfer learn or apply in another country its q…

I have pushed a new version that also supports the canonical format (in json). A quick test with my vitals sign template and the prompt template of the mcp server showed that this works, albeit slower with Claude to populate a composition (77secs vs 45 secs for a single test), whilst the first part…

openEHR MCP Server - a plugin to connect LLMs with CDR's

Tool Support

ian.mcnicoll (Ian McNicoll) 28 May 2025 18:21 17

Short node names in English - yes, but this does introduce a real burden for clinical modellers - see the related discussion on PROMS node names Natural language based FLAT format and long container/element names - #20 by ian.mcnicoll

Topic		Replies	Views
openEHR Assistant MCP Server Tool Support mcp , ai	14	383	8 August 2026
openEHR Discourse AI (LLM) Features General Discussion discourse , ai , mcp	5	162	16 March 2026
openEHR Assistant plugin set for AI agents Tool Support tools , mcp , ai	1	78	8 August 2026
AI support on specifications.openehr.org Specifications website , ai , llms	5	118	5 June 2026
openEHR Discourse MCP Setup Guides General Discussion mcp , ai	1	105	28 April 2026
🚀 New Open Source Tool for openEHR: openEHR-CLI Tools	4	175	5 August 2026
EHRBase and ADL2.0 Platform adl , rest-apis , ehrbase	23	880	13 April 2024
Reflections on the Clinician-Centric Approach of openEHR and its impact on Software Engineering Implementation	7	212	28 November 2025
Relationship between FHIR and openEHR HL7 FHIR	22	14823	8 July 2024
What would you like to see in a new openEHR CDR? Tools	13	930	25 March 2023

openEHR MCP Server - a plugin to connect LLMs with CDR's

Related topics