mcp-agent-kit
mcp-agent-kit
一个纯标准库实现的 Model Context Protocol(MCP)服务器与工具平台,适用于 Claude Desktop、Cursor 和自主智能体集群。
快速开始 • 架构 • Claude Desktop 设置 • 对比 • 工程严谨性
架构
Related MCP server: MCP-123
为什么选择 mcp-agent-kit?
官方 MCP SDK 引入了数十个重量级第三方依赖(pydantic、anyio、httpx、starlette),在企业环境中造成了不必要的供应链攻击面和安装阻力。
mcp-agent-kit 使用 100% Python 标准库,提供了 Model Context Protocol 的完整、生产就绪实现:
🚀 零运行时依赖:纯 Python(
json、sys、inspect、dataclasses)。🔒 企业级就绪:即时可审计,零软件包漏洞暴露。
⚡ 超轻量级:亚毫秒级启动时间,非常适合 CLI 工具、无服务器环境以及嵌入式前置部署的智能体集成。
🛠️ 自动生成 Schema:直接从原生 Python 类型提示和 docstring 推断 JSON Schema 定义。
mcp-agent-kit 对比官方 MCP SDK
维度 |
| 官方 Python MCP SDK |
运行时依赖 | 0(仅 Python 标准库) | 18+ 个第三方依赖 |
安装包体积 | ~15 KB | ~42 MB(含传递依赖) |
进程启动时间 | < 1.2 ms | ~120 ms |
审计面 | 单文件 / 零 CVE | 多个供应链依赖 |
传输支持 |
|
|
快速开始
1. 用 20 行代码构建一个 MCP 服务器
from mcp_agent_kit import MCPServer
app = MCPServer(name="my-agent-tools", version="1.0.0")
@app.tool(description="Calculate tax and total invoice amounts")
def calculate_invoice(subtotal: float, tax_rate: float = 0.07) -> dict:
tax = round(subtotal * tax_rate, 2)
return {"subtotal": subtotal, "tax": tax, "total": round(subtotal + tax, 2)}
if __name__ == "__main__":
app.run_stdio()Claude Desktop 集成
将你的服务器直接添加到 claude_desktop_config.json:
{
"mcpServers": {
"my-tools": {
"command": "python",
"args": ["-m", "examples.simple_server"]
}
}
}重启 Claude Desktop,你的自定义工具将立即出现在 Claude 的工具腰带中!🔨
功能特性
完整的 MCP 握手:
initialize、notifications/initialized、ping。动态工具发现:
tools/list,自动生成 JSON schema。健壮的错误边界:
tools/call可隔离工具运行时异常,并向 LLM 返回结构化错误信息,而不会导致 stdio 进程崩溃。零依赖:在 Python 3.10+ 上开箱即用。
工程严谨性与验证
测试:
pytest测试套件 100% 通过,涵盖初始化、工具发现、参数验证和异常处理。依赖:0 个运行时依赖。
作者:Reuben Bowlby — LinkedIn | 简历
企业级规模
mcp-agent-kit 是 HUMMBL 开发者生态系统的一部分。如需企业级多智能体治理(4 阶段终止开关、HMAC 签名的委派令牌和加密审计总线),请访问 github.com/hummbl-io。
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Tools
Related MCP Servers
- AlicenseDqualityDmaintenanceA foundation for building custom local Model Context Protocol (MCP) servers that provide tools accessible to AI assistants like Cursor or Claude Desktop.137MIT
- FlicenseNot gradedqualityDmaintenanceA minimal Python package for easily setting up and running MCP servers and clients, allowing functions to be automatically exposed as tools that LLMs can use with just 2 lines of code.22
- AlicenseNot gradedqualityBmaintenanceA dead simple MCP server for exposing your app functions to AI agents like Claude Desktop.445MIT
- FlicenseNot gradedqualityDmaintenanceEnables building and running MCP servers over streamable HTTP, exposing tools to AI assistants like Cursor, with examples of mounting multiple servers in FastAPI.
Related MCP Connectors
MCP server for Clipkit — gives AI agents a video toolbox via the Clipkit schema.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/hummbl-dev/mcp-agent-kit'
If you have feedback or need assistance with the MCP directory API, please join our Discord server