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
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.
RF2 Snapshot SNOMED-CT release
│
▼ sct ndjson (~10s for 831k concepts)
│
canonical NDJSON artefact
│
├── sct sqlite ──▶ snomed.db (SQL + FTS5, MCP backend)
│ │
│ ├── sct lexical ──▶ keyword search (FTS5)
│ ├── sct tct ──▶ adds a transitive closure table for faster hierarchy queries
│ ├── sct refset ──▶ query reference sets loaded into the SQLite database
│ └── sct mcp ──▶ stdio MCP server (Claude Desktop / Claude Code)
├── sct parquet ──▶ snomed.parquet (DuckDB / analytics)
├── sct markdown──▶ snomed-concepts/ (RAG / LLM file reading) (untested)
└── sct embed ──▶ snomed-embeddings.arrow (semantic vector search)
│
sct semantic ──▶ cosine similarity search (requires Ollama)
sct info <file> inspect any artefact for more information
sct diff --old <f> --new <f> compare two NDJSON releases (untested)
sct gui browser-based UI served over localhost
with graph visualisation and point-and-click exploration.
sct tui experimental terminal UI to explore concepts and relationships.
sct completions <shell> generate shell completions (optional)The NDJSON artefact at the centre is a stable, versionable, greppable file. All other outputs are derived from it 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:
cargo install cargo-binstall
cargo binstall sct-rs ```
git clone https://github.com/pacharanero/sct
cd sct
cargo install --path . # default build
cargo install --path . --features tui # with terminal UI
cargo install --path . --features gui # with browser UI
cargo install --path . --features full # both| Feature | What it adds | Extra dependencies |
|---|---|---|
| (default) | All non-interactive subcommands | — |
tui | Keyboard-driven terminal UI (sct tui) | ratatui, crossterm |
gui | Browser-based graph UI (sct gui) | axum, tokio, open |
full | Both of the above | all of the above |
```bash
| 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 831k concepts. sct handled it in under a minute.
For more detailed benchmarks, see docs/benchmarks.md. Feel free to run the benchmarks yourself 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 |
| 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：2026-06-03 · 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