protein-design-mcp
by jasonkim8652
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEVICE | No | Device to use: 'auto', 'cuda', or 'cpu'. | auto |
| CACHE_DIR | No | Cache directory. | ~/.cache/protein-design-mcp |
| MODAL_URL | No | URL of the Modal endpoint for cloud GPU deployment. | |
| TORCH_HOME | No | ESM model weights directory (PyTorch default). | |
| PROTEINMPNN_PATH | No | Path to ProteinMPNN installation. | /opt/ProteinMPNN |
| RFDIFFUSION_PATH | No | Path to RFdiffusion installation. | /opt/RFdiffusion |
| COLABFOLD_BACKEND | No | ColabFold backend: 'api' or 'local'. | api |
| SKIP_MODEL_DOWNLOAD | No | Skip eager weight download in Docker. | true |
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 | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jasonkim8652/protein-design-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server