{"type":"mcp_server","name":"dicom-mcp","description":"The dicom-mcp repository provides a Model Context Protocol server for DICOM, enabling LLMs to query and interact with medical imaging metadata from DICOM servers. It supports patient data retrieval and","category":"AI","language":"Python","stars":98,"forks":2,"owner":"ChristianHinge","github_url":"https://github.com/ChristianHinge/dicom-mcp","homepage":null,"setup":"## Setup\n\n### Prerequisites\n\n- Python 3.12 or higher\n- A DICOM server to connect to (e.g., Orthanc, dcm4chee, etc.)\n\n### Using pip\n\nInstall via pip:\n\n```bash\npip install dicom-mcp\n```\n\ndicom-mcp requires a YAML configuration file that defines the DICOM nodes and calling AE titles; create a configuration file with the specified structure.\n\nTo run the server, use the command `dicom-mcp /path/to/configuration.yaml` or `uv run dicom-mcp /path/to/configuration.yaml`.\n\nTo use with Claude Desktop, add the provided configuration to `claude_desktop_config.json`.\n\nTo use with Zed, add the provided configuration to your Zed settings.json.\n\nFor development:\n\n1. Clone the repository: `git clone https://github.com/yourusername/dicom-mcp.git` and `cd dicom-mcp`.\n2. Create a virtual environment: `python -m venv .venv` and activate it with `source .venv/bin/activate` (or `.venv\\Scripts\\activate` on Windows).\n3. Install dependencies: `pip install -e .`.\n\nTo run tests, start an Orthanc server using Docker with `cd tests` and `docker-compose up -d`, then run tests with `pytest tests/test_dicom_mcp.py` or `pytest tests/test_dicom_pdf.py`.","tools":"## Available Tools\n\n1. `list_dicom_nodes` (Lists all configured DICOM nodes and calling AE titles)\n2. `switch_dicom_node` (Switches to a different configured DICOM node)\n3. `switch_calling_aet` (Switches to a different configured calling AE title)\n4. `verify_connection` (Tests connectivity to the configured DICOM node using C-ECHO)\n5. `query_patients` (Search for patients matching specified criteria)\n6. `query_studies` (Search for studies matching specified criteria)\n7. `query_series` (Search for series within a study)\n8. `query_instances` (Search for instances within a series)\n9. `get_attribute_presets` (Lists available attribute presets for queries)\n10. `retrieve_instance` (Retrieves a specific DICOM instance and saves it to the local filesystem)\n11. `extract_pdf_text_from_dicom` (Retrieves a DICOM instance containing an encapsulated PDF and extracts its text content)","faq":null,"created_at":"2025-03-11T16:58:30+00:00","updated_at":"2025-03-28T09:43:38+00:00","source_url":"https://model-context-protocol.com/servers/dicom-llm-medical-imaging-metadata-protocol","related_articles":[]}