open-med-mcp
by d0ng231
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OMM_HOME | No | Weights and Apptainer images. Default: ~/.cache/open-med-mcp | |
| OMM_DEVICE | No | cpu, cuda, cuda:1. Default: auto | |
| OMM_RUNNER | No | local / docker / apptainer; auto = local if importable, else docker, else apptainer. Default: auto | |
| OMM_WORKSPACE | No | Root for relative paths; outputs go to <workspace>/omm_outputs/. Default: current directory. | |
| OMM_MODEL_DIRS | No | Extra adapters (:-separated). Default: - | |
| OMM_IMAGE_PREFIX | No | Registry prefix for container images. Default: ghcr.io/d0ng231/open-med-mcp | |
| OMM_GUIDELINE_DIRS | No | Extra guidelines (:-separated). Default: - | |
| OMM_ZOO_<ADAPTER>_PYTHON | No | Interpreter of a dedicated venv for a local adapter (e.g. OMM_ZOO_SAM2_PYTHON). Default: current interpreter. | |
| OMM_ALLOW_OUTSIDE_WORKSPACE | No | Set false to confine file access to the workspace. Default: true |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues