AI Skill Hub 强烈推荐:Runx 是一款优质的MCP工具。AI 综合评分 8.0 分,在同类工具中表现稳健。如果你正在寻找可靠的MCP工具解决方案,这是一个值得深入了解的选择。
Runx 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。
Runx 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/runxhq/runx
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"runx": {
"command": "npx",
"args": ["-y", "runx"]
}
}
}
# 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 Runx 执行以下任务... Claude: [自动调用 Runx 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": {
"runx": {
"command": "npx",
"args": ["-y", "runx"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"><strong>the governed runtime for agent skills</strong></p>
<p align="center"> <a href="LICENSE"><img alt="license: Apache-2.0" src="https://img.shields.io/badge/license-Apache--2.0-111111?style=flat-square"></a> <a href="https://www.npmjs.com/package/@runxhq/cli"><img alt="npm @runxhq/cli" src="https://img.shields.io/npm/v/@runxhq/cli?style=flat-square&color=cb3837&label=%40runxhq%2Fcli"></a> <a href="https://github.com/runxhq/runx/actions/workflows/ci.yml"><img alt="CI" src="https://github.com/runxhq/runx/actions/workflows/ci.yml/badge.svg"></a> <a href="https://runx.ai/x"><img alt="catalog" src="https://img.shields.io/badge/catalog-runx.ai%2Fx-ff2e88?style=flat-square"></a> <a href="https://runx.ai/spec"><img alt="spec" src="https://img.shields.io/badge/spec-read-7c5cff?style=flat-square"></a> </p>
---
a skill is a URL.
a graph is what unfolds.
authority narrows. it does not pass through.
every act produces a receipt.
A skill is expertise published as a portable SKILL.md: an operating manual that a human can understand and an agent can act from. Skills compose into graphs and real work without bespoke glue code. Runx supplies the boundary: it admits each act under explicit authority, delivers credentials without turning them into prompt material, supervises execution, and seals the result into a verifiable receipt.
Authority narrows through the chain, so agent work compounds without becoming ambient trust.
```
Then choose how you want to run skills.
runx skill sourcey -i project=. --json
This README has an agent-readable twin at runx.ai/SKILL.md. Give it to an agent and the agent learns the CLI, the catalog at runx.ai/x, and how to return receipts.
Install the CLI:
```bash npm i -g @runxhq/cli
Use this package to prove the local execution and receipt path.
When a skill needs deterministic execution, typed inputs, graph stages,
authority, artifacts, or harness cases, it also carries an `X.yaml` execution
profile:
yaml skill: hello-world version: "0.1.0"
runners: default: default: true type: cli-tool command: node args: [run.mjs] inputs: message: type: string required: true ```
The split is deliberate:
- SKILL.md owns the knowledge a human and acting agent need. - X.yaml owns machine-checkable execution, authority, and evidence contracts. - package JavaScript exists only for deterministic domain computation that the graph and native capability plane cannot express cleanly. - HTTP, filesystem, process, credential, packet, and receipt mechanics belong to the runtime, not copied helpers inside skills.
Runx digest-binds the complete current manual into the acting context and the resume envelope. Declared adjacent skills contribute bounded summaries until invoked; invocation then supplies that skill's complete manual.
See Skill to Graph and Skill Catalog.
These checked-in paths produce receipts rather than screenshots or prose-only claims:
| Demo | What it proves | Run |
|---|---|---|
examples/hello-world | Native CLI skill path and sealed receipt baseline | runx harness examples/hello-world |
skills/business-ops | One signal fans through governed lanes and preserves a graph receipt | runx harness skills/business-ops |
examples/github-mcp-hero | Governed read succeeds and an out-of-scope write is refused | sh examples/github-mcp-hero/run.sh |
examples/http-graph | Native governed HTTP executes against a local fixture | sh examples/http-graph/run.sh |
examples/openapi-graph | An OpenAPI operation uses the external-adapter lane | sh examples/openapi-graph/run.sh |
See Demos.
Run a local or catalog skill directly:
runx skill <skill-ref> [runner] -i key=value --json
Seal a receipt locally in under five minutes, with no account and no hosted surface:
npm i -g @runxhq/cli
git clone --depth 1 https://github.com/runxhq/runx.git
cd runx
runx skill ./examples/hello-world -i message="hello, runx" --json
The checked-in examples/hello-world skill runs a local command, and the final --json output includes the sealed receipt (runx.receipt.v1).
business-ops is one prebuilt skill for routing a business signal end to end:
runx skill business-ops \
-i signal="acme.com signed up 40 seats yesterday: classify the work, prepare the governed handoffs, and preserve proof" \
--json
<picture> <source media="(prefers-color-scheme: dark)" srcset="docs/assets/ops-fanout-dark.svg"> <source media="(prefers-color-scheme: light)" srcset="docs/assets/ops-fanout-light.svg"> <img alt="one goal chaining through governed skill lanes into a sealed receipt" src="docs/assets/ops-fanout-light.svg"> </picture>
The graph is the core shape. One signal enters, skills chain under governed authority, consequential lanes hold at approval gates, and every act seals into one receipt tree that can feed the next run. The demo lanes are stand-ins; real teams bind their own context, policies, tools, providers, and readbacks.
Some other examples:
```bash
Runx是一个高质量的开源MCP工具,具有良好的扩展性和可用性
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。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
总体来看,Runx 是一款质量优秀的MCP工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | runx |
| 原始描述 | 开源MCP工具:the governed runtime for agent skill workflows, off the leash but on the record。⭐29 · Rust |
| Topics | agent-orchestrationagent-runtimeagent-skillsagentic-aiai-agents |
| GitHub | https://github.com/runxhq/runx |
| License | MIT |
| 语言 | Rust |
收录时间:2026-06-28 · 更新时间:2026-07-03 · License:MIT · 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