Design archetypes, constrain templates and write AQL using an assistant that looks up answers in the CKM and the published specifications.
MIT-licensed and open source. Use Cadasto's hosted endpoint, or self-host it.
Archetypes come from CKM, type definitions from the BMM schemas, guidance from a corpus written against the published specifications. The server answers from those sources, not from a model's memory.
Search published archetypes and templates by concept, filtering archetypes by RM class. Pull an archetype back as ADL, XML, or a mindmap, and a template as OET or OPT – all within the editor you are already modelling in.
CKM, guides, examples, terminology, and type specifications – reachable from Claude Code, Cursor, Claude Desktop, LibreChat, or anything else that speaks the protocol.
With the plugin, the relevant implementation guide is read before the answer is written, so you get the convention and its anti-pattern – not just something that parses.
A knowledge and authoring server, not a clinical data repository. It reads specifications and published archetypes – it never stores patient data.
Use Cadasto's endpoint, or run your own instance over streamable HTTP or stdio.
The knowledge and tooling layer: tools, prompts, resources, and completions. Connect once from Claude Desktop, Cursor, LibreChat, or any MCP client.
The workflow layer for Claude Code and Cursor: skills, slash commands, and subagents that know when to load guides and call MCP tools.
Point any MCP client at Cadasto's endpoint:
{
"mcpServers": {
"openehr-assistant-mcp": {
"type": "streamable-http",
"url": "https://openehr-assistant-mcp.apps.cadasto.com/"
}
}
}