mcp_server_twomeme_4
MCP 服务配置
复制以下 JSON 到 OPClaw 或其他 MCP 客户端的配置文件中即可使用
{
"mcpServers": {
"crc-lnm-research-assistant": {
"args": [
"crc-lnm-medical-agent@1.0.10"
],
"command": "uvx",
"env": {
"UV_TORCH_BACKEND": "cpu"
}
}
}
}该服务需要配置环境变量：UV_TORCH_BACKEND
可用工具 （6 个）
该服务在 MCP 协议中暴露的工具，AI 可按需调用
crc_lnm_get_model_info 4 个参数 需填 4 项
必填参数：contract_version、request_id、trace_id、input
crc_lnm_case_data_qc 5 个参数 需填 5 项
必填参数：contract_version、request_id、trace_id、case_ref、input
crc_lnm_prepare_ct_features 5 个参数 需填 5 项
必填参数：contract_version、request_id、trace_id、case_ref、input
crc_lnm_prepare_pathology_features 5 个参数 需填 5 项
必填参数：contract_version、request_id、trace_id、case_ref、input
crc_lnm_predict_multimodal 5 个参数 需填 5 项
必填参数：contract_version、request_id、trace_id、case_ref、input
crc_lnm_generate_report 5 个参数 需填 5 项
必填参数：contract_version、request_id、trace_id、case_ref、input
服务介绍
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
| Field Name | Value to Enter |
|---|---|
| Command / 命令 | uvx |
| Argument 1 / 参数1 | crc-lnm-medical-agent@1.0.10 |
| Argument 2 / 参数2 | --transport |
| Argument 3 / 参数3 | stdio |
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
- Build and inspect the wheel, then run the console entry point from an unrelated
working directory. - Publish the verified wheel to PyPI and start it with the exact
uvxcommand above. - Let ModelScope complete
list_tools, then manually test each required tools. - 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
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.
