pywss MCP Server

pywss MCP Server

A lightweight Python web framework that enables building MCP servers with SSE, StreamHTTP, and MCPO protocols for tool integration.

Category
Visit Server

README

<div align='center'>

pywss

<br/>

Project status PyPI Codecov GitHub issues GitHub issues GitHub license

<br/>

</div>

Pywss 简介

Pywss(发音 /piːwaɪz/,类似 p~whys)是一个轻量级的 Python Web 框架,它基于 Python3.6+ 特性构建。

与 Flask、Django 等主流框架不同的是,Pywss 的底层并没有实现 WSGI 接口协议。 其编程风格也更类似于 Gin、Iris 等框架,因此对于熟悉这些框架的开发者来说,Pywss 是一个非常值得探索的项目。

其关键特性有:

  • 简单:拒绝海量参数,减少心智负担。了解上下文 pywss.Context 即刻启程。
  • 快速:引入线程池机制,减少并发场景下线程创建/销毁开销。
  • 优雅ctx.next 真的太优雅了。如果你也和我一样喜欢,那我觉得这件事情,泰裤辣!!
  • 标准化:集成了部分 OpenAPI(Swagger)能力,方便开发者快速生成 API 文档并进行调试。
  • 支持WebSocket:开箱即用的 WebSocket 能力。
  • 接口测试:开箱即用的 API 测试模块,不启动服务也能测试接口功能辣!
  • MCP PRO:一站式集成 SSE、StreamHTTP 和 MCPO 协议,助你轻松构建多 MCP 工具🔥

在线文档 https://czasg.github.io/pywss/

<br/>

快速开始

1、安装 pywss

pip3 install pywss

2、搭建 web 应用

首先创建 main.py 文件,并写入以下代码:

import time
import pywss

def log_handler(ctx: pywss.Context):
    start_time = time.time()
    ctx.next()
    print(
        f"Route: {ctx.route}, "
        f"Method: {ctx.method}, "
        f"Status: {ctx.response_status_code}, "
        f"Time: {time.time() - start_time:.3f}s"
    )

def handler(ctx: pywss.Context):
  ctx.write("hello~")

def main():
    app = pywss.App()
    app.get("/hello", handler)  # curl localhost:8080/hello
    app.any("*", log_handler, handler)  # curl -X POST localhost:8080/hello
    app.run()

if __name__ == '__main__':
    main()

接着启动服务:

python3 main.py

至此,一个简单的 web 应用服务就完成了。

3、搭建 MCP 应用

要快速构建 MCP 服务,只需继承 pywss.mcp.MCPServer 并遵循以下规则:

核心约束:

  • 所有接口方法必须以 tool_ 开头(如 tool_query_user
  • 必须使用 @pywss.openapi.docs 声明请求参数,且 request 必须从 pydantic.BaseModel 继承(自动生成 OpenAPI 文档)

请求处理:

  • 通过 ctx.data.req 直接获取结构化请求体
  • 使用 self.handle_success(ctx, data) 返回成功响应
  • 使用 self.handle_error(ctx, code, message) 返回标准错误
# coding: utf-8
import pywss
from pydantic import BaseModel
from pywss.mcp import MCPServer

class DomainReq(BaseModel):  # 定义 DomainReq 请求,必须从 pydantic.BaseModel 继承
    domain: str

class DomainMCPServer(MCPServer):  # 定义 DomainMCPServer 服务,必须从 pywss.mcp.MCPServer 继承
    @pywss.openapi.docs(description="获取单个域名服务", request=DomainReq)  # required,工具及其参数说明
    def tool_get_domain(self, ctx: pywss.Context):
        req: DomainReq = ctx.data.req  # 框架已经封装好了请求,可以从 ctx.data.req 直接获取使用,异常请求会被拦截
        self.handle_success(ctx, {  # handle_success 封装了 jsonrpc2.0 输出规范
            "domain": req.domain,
            "color": req.color
        })

class LogReq(BaseModel):
    traceId: str

class LogMCPServer(MCPServer):
    @pywss.openapi.docs(description="获取单个trace日志", request=LogReq)
    def tool_get_trace_log(self, ctx: pywss.Context):
        req: LogReq = ctx.data.req
        self.handle_success(ctx, {
            "traceId": req.traceId,
        })

domainMCPServer = DomainMCPServer()
logMCPServer = LogMCPServer()

app = pywss.App()
app.openapi()  # 开启 OpenAPI 文档
domainMCPServer.mount(app.group("/api/v1/domain"))  # 挂载 MCP 服务,同时指定路由
logMCPServer.mount(app.group("/api/v1/log"))  # 挂载 MCP 服务,同时指定路由
app.run()

接着启动服务:

python3 main.py
协议类型 服务类 请求方法 端点路径格式 示例路径
SSE domainMCPServer GET /api/v1/domain/sse GET /api/v1/domain/sse
logMCPServer GET /api/v1/log/sse GET /api/v1/log/sse
StreamHTTP domainMCPServer POST /api/v1/domain/mcp POST /api/v1/domain/mcp
logMCPServer POST /api/v1/log/mcp POST /api/v1/log/mcp
MCPO domainMCPServer POST /api/v1/domain/tools/{tool_name} POST /api/v1/domain/tools/get_domain
logMCPServer POST /api/v1/log/tools/{tool_name} POST /api/v1/log/tools/get_trace_log

更多功能见在线文档

<br/>

Activity

Alt

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured