Best Practices MCP Server

Best Practices MCP Server

Provides Python and FastAPI coding best practices with searchable guidelines, code review capabilities, and actionable improvement suggestions with examples across general coding, performance, and code quality categories.

Category
访问服务器

README

Best Practices MCP Server

A Model Context Protocol (MCP) server that provides Python coding best practices and guidelines for general coding and API development using FastAPI.

Features

  • Search Best Practices: Search by keyword across all categories
  • Category Browsing: Explore practices by category (general_coding, fastapi_specific, performance, code_quality)
  • Code Examples: Get practical code examples for specific topics
  • Code Review: Analyze code against best practices with specific recommendations
  • Improvement Suggestions: Get prioritized, actionable improvements with before/after examples
  • MCP Resources: Access best practices via URI (e.g., bestpractices://fastapi/async_operations)
  • Pre-built Prompts: Quick access to common tasks like code review and examples

Installation

pip install -r requirements.txt

Configuration

The server supports the following environment variables:

  • BEST_PRACTICES_FILE: Path to the best practices JSON file (default: data/python_best_practices.json)
  • LOG_LEVEL: Logging level (default: INFO)

Example:

export BEST_PRACTICES_FILE=/path/to/custom_practices.json
export LOG_LEVEL=DEBUG

Running the Server

python bestpractices_mcp_server.py

Usage with Kiro IDE

  1. Add the server to your MCP configuration (.kiro/settings/mcp.json):
{
  "mcpServers": {
    "bestpractices": {
      "command": "python",
      "args": ["/path/to/bestpractices_mcp_server.py"],
      "env": {
        "BEST_PRACTICES_FILE": "data/python_best_practices.json"
      }
    }
  }
}
  1. Restart Kiro IDE or reconnect the MCP server

  2. Use the tools in your AI assistant conversations

Available Tools

search_best_practices

Search for best practices by keyword.

search_best_practices(keyword="async")

get_practice_by_category

Get practices for a specific category or topic.

get_practice_by_category(category="fastapi_specific", topic="pydantic_models")

list_categories

List all available categories.

list_categories()

get_examples_tool

Get code examples for a specific topic.

get_examples_tool(topic="type_hints")

review_code

Review code against best practices.

review_code(code="def test(): pass", context="general")

suggest_improvements

Get improvement suggestions for code.

suggest_improvements(code="def test(): pass", focus_area="type_hints")

Available Resources

Access best practices directly via URI:

  • bestpractices://general/{topic} - General Python practices
  • bestpractices://fastapi/{topic} - FastAPI-specific practices
  • bestpractices://performance/{topic} - Performance optimization
  • bestpractices://code_quality/{topic} - Code quality practices
  • bestpractices://all - Complete guide

Available Prompts

  • review_python_code - Comprehensive Python code review
  • review_fastapi_endpoint - FastAPI-specific code review
  • suggest_code_improvements - Get improvement suggestions
  • show_examples - Retrieve examples for a topic

Best Practices Database

The server reads from data/python_best_practices.json which contains:

  • general_coding: Naming conventions, type hints, error handling, documentation, code organization
  • fastapi_specific: Routes, Pydantic models, dependency injection, async operations, middleware, security
  • performance: Caching, database optimization
  • code_quality: Linting, logging

The database is read dynamically on each request, so updates are reflected immediately without restarting the server.

Examples

The examples/ directory contains usage examples demonstrating the server's functionality:

  • search_example.py - Search for best practices by keyword
  • code_review_example.py - Review code against best practices
  • resource_access_example.py - Access practices via categories and topics

Run examples:

python examples/search_example.py
python examples/code_review_example.py
python examples/resource_access_example.py

See examples/README.md for detailed documentation.

Development

Running Tests

pytest test_data_manager.py -v

Adding New Best Practices

Edit data/python_best_practices.json and add your practices following the structure:

{
  "python_best_practices": {
    "category_name": {
      "topic_name": {
        "description": "Description of the practice",
        "examples": {
          "example_name": "code example"
        }
      }
    }
  }
}

Troubleshooting

Server won't start

  • Check that data/python_best_practices.json exists
  • Verify the JSON file is valid
  • Check file permissions

No results from search

  • Verify the keyword exists in the database
  • Try broader search terms
  • Use list_categories() to see available topics

Tools not appearing in Kiro

  • Verify MCP configuration is correct
  • Restart Kiro IDE
  • Check server logs for errors

License

MIT License

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选