mcp-dynamic-orchestrator

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Overview

概述

Use this skill to:

Discover which MCP servers are available and what they are for.
Inspect a specific MCP's capabilities without loading all tool schemas.
Execute TypeScript/JavaScript that calls MCP tools via generated
```
mcp-clients/*
```
modules.

If no MCP servers are configured,

list_mcp_capabilities

will respond with an empty list and a message pointing to

skills/mcp-dynamic-orchestrator/mcp.registry.json

so the user can add MCP entries.

This skill reads from

mcp.registry.json

, so adding an MCP entry there (for example the Cloudflare MCP) automatically makes it discoverable without changing tool wiring.

使用此技能可实现：

发现可用的MCP服务器及其用途。
无需加载所有工具架构即可检查特定MCP的功能。
执行通过生成的
```
mcp-clients/*
```
模块调用MCP工具的TypeScript/JavaScript代码。

如果未配置任何MCP服务器，

list_mcp_capabilities

将返回空列表，并给出指向

skills/mcp-dynamic-orchestrator/mcp.registry.json

的提示信息，以便用户添加MCP条目。

此技能读取

mcp.registry.json

文件，因此在其中添加MCP条目（例如Cloudflare MCP）后，无需修改工具连接即可自动使其可被发现。

Cloudflare MCP example

Cloudflare MCP示例

The Cloudflare MCP server can be configured in

mcp.registry.json

like this:

json

{
  "id": "cloudflare",
  "title": "Cloudflare platform MCP",
  "summary": "Interact with Cloudflare's MCP endpoint for documentation, examples, and platform operations exposed via the official Cloudflare MCP server.",
  "mcp": {
    "transport": "stdio",
    "command": "npx",
    "args": [
      "mcp-remote",
      "https://docs.mcp.cloudflare.com/sse"
    ]
  },
  "domains": ["cloudflare", "workers", "kv", "r2", "queues", "zero_trust", "networking", "security", "observability"],
  "tags": ["cloudflare", "platform", "infra", "docs", "workers", "mcp"],
  "examples": [
    "Fetch Cloudflare Workers documentation for a specific API.",
    "Search Cloudflare platform docs for queues or KV usage patterns.",
    "Look up configuration guidance for Zero Trust or networking features."
  ],
  "sensitivity": "low",
  "visibility": "default",
  "priority": 10,
  "autoDiscoverTools": true
}

With this entry present:

```
list_mcp_capabilities
```
will return
```
cloudflare
```
when queries mention Cloudflare, Workers, KV, R2, Queues, etc.
```
describe_mcp
```
with
```
id: "cloudflare"
```
will surface concise tool summaries from the Cloudflare MCP server.
```
execute_mcp_code
```
lets the agent write TypeScript such as:

import * as cloudflare from "mcp-clients/cloudflare";

async function main() {
  const docs = await cloudflare.search_docs({ query: "Workers KV" });
  console.log(docs.summary);
}

The actual available functions under

mcp-clients/cloudflare

are generated dynamically from the MCP tool definitions; the agent should always:

Discover via
```
list_mcp_capabilities
```
.
Inspect via
```
describe_mcp
```
to see available operations.
Use those operations via
```
execute_mcp_code
```
.

Cloudflare MCP服务器可在

mcp.registry.json

中按如下方式配置：

json

{
  "id": "cloudflare",
  "title": "Cloudflare platform MCP",
  "summary": "Interact with Cloudflare's MCP endpoint for documentation, examples, and platform operations exposed via the official Cloudflare MCP server.",
  "mcp": {
    "transport": "stdio",
    "command": "npx",
    "args": [
      "mcp-remote",
      "https://docs.mcp.cloudflare.com/sse"
    ]
  },
  "domains": ["cloudflare", "workers", "kv", "r2", "queues", "zero_trust", "networking", "security", "observability"],
  "tags": ["cloudflare", "platform", "infra", "docs", "workers", "mcp"],
  "examples": [
    "Fetch Cloudflare Workers documentation for a specific API.",
    "Search Cloudflare platform docs for queues or KV usage patterns.",
    "Look up configuration guidance for Zero Trust or networking features."
  ],
  "sensitivity": "low",
  "visibility": "default",
  "priority": 10,
  "autoDiscoverTools": true
}

添加此条目后：

当查询提及Cloudflare、Workers、KV、R2、Queues等内容时，
```
list_mcp_capabilities
```
将返回
```
cloudflare
```
。
使用
```
id: "cloudflare"
```
调用
```
describe_mcp
```
将显示来自Cloudflare MCP服务器的简洁工具摘要。
```
execute_mcp_code
```
允许Agent编写如下TypeScript代码：

import * as cloudflare from "mcp-clients/cloudflare";

async function main() {
  const docs = await cloudflare.search_docs({ query: "Workers KV" });
  console.log(docs.summary);
}

mcp-clients/cloudflare

下实际可用的函数是从MCP工具定义中动态生成的；Agent应始终遵循以下步骤：

通过
```
list_mcp_capabilities
```
进行发现。
通过
```
describe_mcp
```
检查可用操作。
通过
```
execute_mcp_code
```
使用这些操作。

How to use

使用方法

Call
```
list_mcp_capabilities
```
with a natural language query or filters to see which MCPs exist.
For a chosen MCP (e.g.
```
cloudflare
```
), call
```
describe_mcp
```
to understand its operations.
Write TypeScript/JavaScript that imports from
```
mcp-clients/<id>
```
and calls the exported functions.
Run your code with
```
execute_mcp_code
```
, optionally restricting
```
allowedMcpIds
```
for safety.

调用
```
list_mcp_capabilities
```
并传入自然语言查询或筛选条件，查看存在哪些MCP。
对于选定的MCP（例如
```
cloudflare
```
），调用
```
describe_mcp
```
了解其操作。
编写从
```
mcp-clients/<id>
```
导入并调用导出函数的TypeScript/JavaScript代码。
使用
```
execute_mcp_code
```
运行代码，可选择性地限制
```
allowedMcpIds
```
以保障安全。

Rules

规则

Do not assume individual MCP tools are top-level tools.
Always: discover → describe → generate code →
```
execute_mcp_code
```
.
Request
```
detail: "schema"
```
in
```
describe_mcp
```
only when exact parameter shapes are required.

不要假设单个MCP工具是顶级工具。
始终遵循：发现 → 描述 → 生成代码 →
```
execute_mcp_code
```
的流程。
仅当需要确切参数格式时，才在
```
describe_mcp
```
中请求
```
detail: "schema"
```
。

Known Limitations

已知限制

Sandbox Security (CRITICAL)

沙箱安全性（CRITICAL）

⚠️ The current sandbox implementation is NOT secure for untrusted code.

Uses
```
vm.createContext()
```
which is NOT a security boundary
Can be escaped via prototype pollution, require() manipulation, etc.
Only enable for Claude-generated code (trusted source)
Requires
```
MCP_ORCH_ENABLE_SANDBOX=1
```
environment variable
See
```
references/security-model.md
```
for complete security details

⚠️ 当前沙箱实现对于不可信代码并不安全。

使用
```
vm.createContext()
```
，这并非安全边界
可通过原型污染、require()操纵等方式逃逸
仅对Claude生成的代码启用（可信来源）
需要设置
```
MCP_ORCH_ENABLE_SANDBOX=1
```
环境变量
完整安全细节请参阅
```
references/security-model.md
```

Other Limitations

其他限制

No TypeScript compilation: User code in
```
.ts
```
format will fail
No module resolution: Imports from
```
mcp-clients/*
```
don't resolve; use
```
$call()
```
API
Static registry: Adding/removing MCPs requires restart
Limited error handling: Generic errors for MCP connection failures

For detailed troubleshooting, see

references/troubleshooting.md

无TypeScript编译：
```
.ts
```
格式的用户代码将执行失败
无模块解析：无法解析
```
mcp-clients/*
```
的导入；请使用
```
$call()
```
API
静态注册中心：添加/移除MCP需要重启服务
有限的错误处理：MCP连接失败时仅返回通用错误

详细故障排除请参阅

references/troubleshooting.md

。

Production Status

生产状态

What's Working ✅:

Discovery via
```
list_mcp_capabilities
```
(fully functional)
Inspection via
```
describe_mcp
```
(fully functional)
Registry management (16 MCPs configured)
MCP clients (stdio + HTTP transports)
Safety controls (visibility, sensitivity, policies)

What's Limited 🟡:

Code execution (requires env flag, sandbox not secure)
Testing (basic smoke tests only)

What's Planned 🔮:

Secure sandbox with Worker threads (v1.1)
TypeScript compilation support (v1.1)
Module resolution (v1.1)
Dynamic registry updates (v1.2)

For complete roadmap, see

plan.md

in repository root.

已实现功能 ✅:

通过
```
list_mcp_capabilities
```
进行发现（功能完整）
通过
```
describe_mcp
```
进行检查（功能完整）
注册中心管理（已配置16个MCP）
MCP客户端（stdio + HTTP传输）
安全控制（可见性、敏感度、策略）

功能受限 🟡:

代码执行（需要环境变量标记，沙箱不安全）
测试（仅基础冒烟测试）

计划功能 🔮:

基于Worker线程的安全沙箱（v1.1）
TypeScript编译支持（v1.1）
模块解析（v1.1）
动态注册中心更新（v1.2）

完整路线图请参阅仓库根目录下的

plan.md

。