CRC-LNM Multimodal Research Assistant MCP

This MCP server provides a six-tool, research-assistance workflow for allowlisted, deidentified CRC-LNM cases. It accepts only precomputed 1409-dimensional CT features, 768-dimensional pathology features, and four clinical values. It does not accept raw imaging files, file paths, or external feature vectors.

ModelScope STDIO Deployment (Quick Start)

Step 1: Select Service Type

Select "STDIO" (NOT "Streamable HTTP")

Step 2: Fill These Fields Separately

Step 3: Set Environment Variable

Find the environment variable field and add:

UV_TORCH_BACKEND=cpu

Step 4: Deploy

Click deploy and wait for list_tools to complete with 6 tools.

Verification Order

1. Build and inspect the wheel, then run the console entry point from an unrelated working directory.
2. Publish the verified wheel to PyPI and start it with the exact uvx command above.
3. Let ModelScope complete list_tools, then manually test each required tools.
4. Obtain the ModelScope URL, add it as a Nexent custom MCP service, enable the six tools, debug the agent, and verify a post-publication question.

Technical Reference

MCP Server Configuration

{
  "mcpServers": {
    "crc-lnm-research-assistant": {
      "command": "uvx",
      "args": [
        "crc-lnm-medical-agent@1.0.10",
        "--transport",
        "stdio"
      ],
      "env": {
        "UV_TORCH_BACKEND": "cpu"
      }
    }
  }
}

Why UV_TORCH_BACKEND=cpu?

Required so the hosted Linux installation resolves CPU PyTorch packages instead of CUDA runtime packages.

Why STDIO?

The published wheel contains the immutable model bundle and trusted release JSONL. On first launch it creates a verified case-package cache and transient artifacts in a writable system cache directory. No local path argument is required.

docs/PLATFORM_DEPLOYMENT.md covers the separate authenticated Streamable HTTP container path. 使用说明.md documents the local release workflow and constraints.