openEHR MCP Server
Enables MCP clients like Claude Desktop to interact with openEHR REST APIs (EHRbase) for creating compositions, managing EHRs, listing templates, and executing AQL queries.
README
openEHR MCP Server
An MCP (Model Context Protocol) server designed to interface with openEHR REST APIs, specifically the EHRbase implementation. This server enables MCP clients like Claude Desktop to create compositions for openEHR templates and submit them to a server. For production grade EHR integrations you must use an AI Model where you can ensure data privacy.
See https://modelcontextprotocol.io/introduction for more information about MCP.
Version
Current version: 0.1.0
This project follows semantic versioning. For details on our versioning strategy, see VERSIONING.md.
MCP Tools
- openehr_template_list: List all available openEHR templates from the EHRbase server
- openehr_template_get: Retrieve a specific openEHR template by its unique identifier
- openehr_template_example_composition: Generate an example openEHR composition based on a specific template
- openehr_ehr_create: Create a new EHR in the system
- openehr_ehr_get: Retrieve an EHR by its ID
- openehr_ehr_list: List all available EHRs in the system
- openehr_ehr_get_by_subject: Get an EHR by subject ID and namespace
- openehr_composition_create: Create a new openEHR composition in the Electronic Health Record
- openehr_composition_get: Retrieve an existing openEHR composition by its unique identifier
- openehr_composition_update: Update an existing openEHR composition in the Electronic Health Record
- openehr_composition_delete: Delete an existing openEHR composition from the Electronic Health Record
- openehr_query_adhoc: Execute an ad-hoc AQL query against the openEHR server
MCP Prompts
- vital_signs_capture: Capture vital signs for a specific EHR ID
MCP Resource
Not yet implemented
Quick Start with Docker
The easiest way to get started is to use the pre-built Docker image available on Docker Hub.
1. Prerequisites
Ensure you have a running EHRbase server. For running one locally, see below.
2. Configure Claude Desktop
Edit your Claude Desktop configuration file (claude_desktop_config.json) and add an "openEHR" configuration block inside the "mcpServers" section.
This file can usually be found in the following locations:
- On macOS: ~/Library/Application Support/Claude
- On Windows: %APPDATA%\Claude
{
"mcpServers": {
"openEHR": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--network=host",
"-e","EHRBASE_URL=http://localhost:8080/ehrbase/rest",
"-e","EHRBASE_JSON_FORMAT=wt_flat",
"ctodeakai/openehr-mcp-server:latest"
]
}
}
}
You can point EHRBASE_URL to your own EHRbase server or use the provided docker-compose setup.
JSON Format Configuration
The MCP server supports different JSON serialization formats for interacting with the EHRbase API. You can configure the format using the optional EHRBASE_JSON_FORMAT environment variable:
"-e", "EHRBASE_JSON_FORMAT=wt_flat"
Available format options:
- wt_flat (default): Use the simplified data types (SDT) based on the flat web template format
- canonical: Uses the canonical openEHR JSON format consistently across all operations
- wt_structured: SDT based on the structured web template format (currently not working)
For more information on how to set up Claude Desktop with MCP servers, see https://modelcontextprotocol.io/quickstart/user.
Setup
Prerequisities
For this MCP server to work, you currently require
- an ehrbase server
- a sample server is provided here: docker-compose.yml
- an openEHR template
- a sample template is provided here: vital_signs_basic.opt
- you can upload one using the script upload_template.py
- an EHR within this server and its associated EHR ID
- you can create one using the script create_ehr.py
Local EHRBase Setup
Prerequisites
- A working Docker installation
- Python 3 (this project was built with python 3.12, earlier versions might work)
- A Python virtual environment (pip, conda or uv)
- Install the required dependencies in your Python environment:
pip install -r requirements.txt
Running the EHRbase Server
-
Navigate to the docker-compose directory:
cd docker-compose -
Start the EHRbase server in detached mode:
docker compose up -d -
Check the logs to verify the server is running properly:
docker compose logs -f -
The EHRbase server will be available at http://localhost:8080/ehrbase/
-
The EHRBase API documentation should be here: http://localhost:8080/ehrbase/swagger-ui/index.html
Uploading the Vital Signs Template
After setting up the EHRbase server and your Python environment, you can upload the vital signs template:
python scripts/upload_template.py
You can also specify a custom template or EHRbase URL:
python scripts/upload_template.py --template path/to/template.opt --ehrbase-url http://custom-url:8080/ehrbase/rest
You should see output confirming the successful upload of the template to the EHRbase server.
Creating an EHR
After uploading the template, you need to create an Electronic Health Record (EHR) to store compositions:
python scripts/create_ehr.py
This will create an EHR with a randomly generated subject ID. You can also specify a custom subject ID:
python scripts/create_ehr.py --subject-id "patient_12345"
The script will output the EHR ID, which you'll need when creating compositions or using the MCP server.
Running the Integration Tests
To run the tests, you'll need to install the test dependencies first:
pip install -r requirements-test.txt
After installing the test dependencies and uploading the template, you can run the tests with:
python -m pytest tests/test_*.py -v
This will run all the tests in the tests directory.
Running the openEHR MCP server with Docker
Building the Docker Image
Build the Docker image from the project root:
docker build -t openehr-mcp-server .
Running the Docker Container
docker run -i --rm --network=host openehr-mcp-server
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.