Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
UV_TORCH_BACKENDNoSet to 'cpu' for CPU PyTorch packages instead of CUDA runtime packages in hosted Linux deployments.
CRC_LNM_MCP_RUNTIME_ROOTNoOptional. Specifies a writable cache location. Defaults to a system cache directory.

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

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
crc_lnm_get_model_infoB

Return integrity-checked model dimensions, version, hashes and threshold.

crc_lnm_case_data_qcB

Validate deidentified case integrity, privacy and required modalities.

crc_lnm_prepare_ct_featuresB

Validate and retain approved precomputed 1409-dimensional CT features.

crc_lnm_prepare_pathology_featuresC

Validate and retain approved 768-dimensional pathology features.

crc_lnm_predict_multimodalC

Run the locked five-member multimodal ensemble after compatibility gates.

crc_lnm_generate_reportC

Generate a deterministic escaped research-assistance report.

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/lisazhanggg0810-source/crc-lnm-medical-agent-legacy'

If you have feedback or need assistance with the MCP directory API, please join our Discord server