Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DEVICENoDevice to use: 'auto', 'cuda', or 'cpu'.auto
CACHE_DIRNoCache directory.~/.cache/protein-design-mcp
MODAL_URLNoURL of the Modal endpoint for cloud GPU deployment.
TORCH_HOMENoESM model weights directory (PyTorch default).
PROTEINMPNN_PATHNoPath to ProteinMPNN installation./opt/ProteinMPNN
RFDIFFUSION_PATHNoPath to RFdiffusion installation./opt/RFdiffusion
COLABFOLD_BACKENDNoColabFold backend: 'api' or 'local'.api
SKIP_MODEL_DOWNLOADNoSkip eager weight download in Docker.true

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

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