Test MCP Server
A basic MCP server implementation for testing purposes. Communicates via stdio and is designed to work with MCP-compliant clients.
README
Test MCP Server
Test MCP Server
Description
Prerequisites
- Python 3.10 or higher.
uv(recommended for dependency management) orpip.
Installation
-
Clone the repository:
git clone <repository-url> cd mcp_test -
Install dependencies:
# Using Python 3.10 or higher with pyenv pyenv install 3.10.0 pyenv local 3.10.0 # Using uv uv venv source .venv/bin/activate uv pip install -r requirements.txt # OR using pip python3 -m venv .venv source .venv/bin/activate pip install -r requirements.txt
Usage
Allow MCP client to run the server using Python: TODO: UPDATE WITH CLAUDE CODE & GOOGLE ANTIGRAVITY SPECIFIC INSTRUCTIONS
The server listens on `stdio` by default. It assumes an MCP-compliant client will start it and communicate via standard input/output.
Commit Pattern
According to Google, there are 11 types of commits (listed below).
Please mark the beginning of your commit with an identifier string indicating what type of commit it is.
This helps keep track of the development cadence and is also useful for extracting relevant information
from commit history. I also realize I am talking to myself here lol.
Example: git commit -m "docs: Adding documentation because I am a responsible engineer"
feat: Introduces a new feature.
fix: Patches a bug in the code.
docs: Changes to documentation only (README, comments).
style: Formatting, whitespace, missing semicolons; no code change in meaning.
refactor: Restructures code without changing functionality (neither a feature nor a fix).
perf: Improves performance.
test: Adds or corrects tests.
build: Changes affecting the build system or external dependencies (npm, webpack).
ci: Changes to CI configuration files and scripts (GitHub Actions, Jenkins).
chore: Maintenance tasks, updating dependencies, build process changes that don't touch src or test files.
revert: Reverts a previous commit.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。