SNOMED-CT 工具 是 AI Skill Hub 本期精选MCP工具之一。综合评分 8.0 分,整体质量较高。我们强烈推荐将其纳入你的 AI 工具库,帮助提升工作效率。
SNOMED-CT 工具 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
SNOMED-CT 工具 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/pacharanero/sct
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"snomed-ct---": {
"command": "npx",
"args": ["-y", "sct"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 SNOMED-CT 工具 执行以下任务... Claude: [自动调用 SNOMED-CT 工具 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"snomed-ct___": {
"command": "npx",
"args": ["-y", "sct"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <img src="docs/assets/logo/sct-logo.svg" width="288" alt="sct logo"> </p>
A local-first SNOMED CT toolchain that's 10-100x faster than IHTSDO Snowstorm. One binary - from raw RF2 release to NDJSON, then SQL, Parquet, Markdown, TUI, GUI, graphs and MCP/LLM tool use. All on your machine, no network calls, REST APIs, or external servers required.
This is very much a work in progress, but it's ready to use and I would very much like feedback on how it performs for you.
Plus sct diff (compare two NDJSON releases), sct info (inspect any artefact), and sct gui / sct tui for visual, point-and-click exploration.
The canonical NDJSON artefact at the centre is stable, versionable, and greppable. The main file contains concepts; --refsets all adds provenance-declared payload-refset and history companion streams so non-concept RF2 rows remain lossless. All other outputs are derived from this NDJSON bundle and can be regenerated at any time.
---
Prebuilt binaries are published for Linux (x86_64, aarch64), macOS (Apple Silicon, Intel), and Windows (x86_64) on every release, with SHA-256 checksums you can verify against the SHA256SUMS file on the Releases page.
cargo install sct-rs
Or, if you have the [`cargo-binstall`](https://github.com/cargo-bins/cargo-binstall) plugin installed (it is not bundled with `cargo` itself), grab a prebuilt binary instead of compiling from source:
bash
cargo install cargo-binstall
cargo binstall sct-rs ```
nix run github:pacharanero/sct -- lookup 22298006
nix profile install github:pacharanero/sct
git clone https://github.com/pacharanero/sct
cd sct
cargo install --path . # default build: core commands + sct serve + sct tui
cargo install --path . --features gui # add the browser UI (sct gui)
cargo install --path . --features dmwb # add the NHS DMWB .mdb reader (sct dmwb)
cargo install --path . --features full # everything: serve + tui + gui + dmwb + diagram SVG
| Feature | Default? | What it adds | Extra dependencies |
|---|---|---|---|
serve | yes | FHIR R4 terminology server (sct serve) | axum, tokio |
tui | yes | Interactive terminal UI - powers both sct tui and the live sct sayt view | ratatui, crossterm |
gui | opt-in | Browser-based graph UI (sct gui) | axum, tokio, open |
dmwb | opt-in | Read NHS Data Migration Workbench .mdb files (sct dmwb) | jetdb |
diagram-svg | opt-in | Built-in SVG output for sct diagram | layout-rs |
full | opt-in | Everything: serve + tui + gui + dmwb + diagram-svg | all of the above |
Every other subcommand (RF2 conversion, SQLite/Parquet/Markdown/Arrow, search, ECL, maps, codelists, MCP, diff, info…) is always compiled in. Only a --no-default-features build - such as the headless Docker server image - drops serve and tui.
```bash
yay -S sct-rs-bin
| Operation | sct + SQLite | Snowstorm Lite | sct speedup |
|---|---|---|---|
| Import - Clinical Edition | 22s | 209s | ~10x faster |
| Import - Full UK Monolith | ~57s | Failed (OOM)* | ∞ |
| Single concept lookup (SCTID) | 6ms | 491ms | ~80x faster |
| Free-text search (10 results) | 2ms | 202ms | ~100x faster |
* Snowstorm Lite running in Docker with 24Gb of Java heap allocation ran out of memory on the full UK Monolith, which has 837,930 concepts. sct handled it in under a minute.
These comparison numbers predate the current 837,930-concept release and haven't been re-run against a live Snowstorm Lite instance since - treat them as indicative rather than current. For up-to-date sct-only timings, see docs/benchmarks.md. Feel free to run the benchmarks yourself (including a fresh Snowstorm Lite comparison) and share your results, perhaps as an Issue.
---
高质量的开源MCP工具,支持多种格式
该工具使用 AGPL-3.0 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
⚠️ AGPL 3.0 — 最严格的 Copyleft,网络服务端使用也需开源,SaaS 使用受限。
经综合评估,SNOMED-CT 工具 在MCP工具赛道中表现稳健,质量优秀。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | sct |
| 原始描述 | 开源MCP工具:SNOMED-CT tooling, brought into the 21stC. RF2 → NDJSON → SQLite | Vector | .arr。⭐16 · Rust |
| Topics | SNOMED-CTMCPRust健康 |
| GitHub | https://github.com/pacharanero/sct |
| License | AGPL-3.0 |
| 语言 | Rust |
收录时间:2026-06-03 · 更新时间:2026-06-05 · License:AGPL-3.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端