AI Skill Hub 强烈推荐:MCP运行时 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。
MCP运行时 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。
MCP运行时 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/contextforge-org/cpex
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"mcp---": {
"command": "npx",
"args": ["-y", "cpex"]
}
}
}
# 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 MCP运行时 执行以下任务... Claude: [自动调用 MCP运行时 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": {
"mcp___": {
"command": "npx",
"args": ["-y", "cpex"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
CPEX is a policy enforcement runtime for AI agents.
It acts as a deterministic reference monitor between an agent and every capability it invokes: tools, prompts, resources, inference providers, and A2A methods. Every operation is evaluated against security state the model cannot observe or influence, including identity, delegation and escalation chains, information-flow labels, and audit log.
CPEX composes authorization, delegation, redaction, information-flow tracking, and auditing into a single policy-defined pipeline. Every operation executes the same deterministic sequence, from identity resolution and policy evaluation through credential delegation, data transformation, session updates, out-of-band approvals, and auditing.
```bash
Each capability exposed to an agent defines its own enforcement pipeline, whether it's a tool, resource, prompt, or A2A method.
APL is the configuration that defines that pipeline. A route identifies an entity and sequences the controls that protect it: resolve identity, consult an external PDP, exchange credentials, invoke plugins, redact results, propagate taint, and audit the operation. Each step executes deterministically, in order, with only the context it explicitly declares.
Policies execute in two phases—before the operation and after its result—making the complete enforcement pipeline easy to inspect and reason about.
cargo add cpex
cargo add cpex --features builtins
The default `cpex = "0.2"` is the **engine alone**. Opt into the bundled extension set with the `builtins` feature, everything (incl. the Valkey session store) with `full`, or a granular subset: `jwt`, `oauth`, `pii`, `audit`, `cedar`, `cel`, `valkey`.
rust use std::sync::Arc; use cpex::PluginManager;
let mgr = Arc::new(PluginManager::default());
// With a builtins feature enabled, register every enabled builtin factory // and install the APL config visitor in one call: cpex::install_builtins(&mgr); // ... then load an APL config that references the enabled plugin kinds. ```
Authoring plugins or PDP resolvers? Depend on the lean cpex-sdk crate instead of the full runtime. See crates/cpex-core/examples for runnable examples.
高性能AI代理策略执行引擎
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。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
总体来看,MCP运行时 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 | cpex |
| Topics | AIMCPRust代理 |
| GitHub | https://github.com/contextforge-org/cpex |
| License | Apache-2.0 |
| 语言 | Rust |
收录时间:2026-06-27 · 更新时间:2026-06-27 · License:Apache-2.0 · 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