MCP All-in-One Server
A versatile MCP server providing tools for arithmetic operations, n8n webhook integration, and access to a customer support playbook resource. It also includes specialized prompt templates for converting webinar transcripts into engaging blog posts.
README
MCP All-in-One Server
This is a versatile MCP server that demonstrates multiple capabilities of the Model Context Protocol (MCP). It provides tools for calculation, external integrations (webhooks), resources for context, and prompt templates.
Capabilities
🧮 Tools
Functions that the AI can execute:
- Calculator: Basic arithmetic operations (
add,subtract,multiply,divide). - Webhook Integration:
send_to_webhook- Sends a text prompt to a configured n8n workflow and returns the response.
📚 Resources
Contextual data the AI can read:
support://playbook: A full Customer Support Playbook containing company overview, tone rules, product details, and standard operating procedures.
📝 Prompts
Templates to structure AI interactions:
webinar_to_blog: A structured prompt template to convert webinar transcripts into engaging blog posts.
Prerequisites
- Python 3.10+
- uv: A fast Python package installer and resolver.
- Windows:
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex" - macOS/Linux:
curl -LsSf https://astral.sh/uv/install.sh | sh
- Windows:
- Node.js & npm (optional, for the MCP Inspector)
Setup
- Open your terminal in this directory (
calculator_server). - Initialize the project (if you haven't already):
uv init - Add the required dependencies:
uv add "mcp[cli]" httpx
Running the Server
You can run the server directly using uv:
uv run server.py
Note: This will use stdio for communication, so it will expect input from stdin and won't show much output in the console unless connected to an MCP client.
Testing with MCP Inspector
To test the server using the MCP Inspector (a web-based tool to interact with your server):
npx @modelcontextprotocol/inspector uv run server.py
This will launch the inspector in your browser. You can:
- Tools: Test the calculator and webhook tools.
- Resources: View the content of
support://playbook. - Prompts: Execute the
webinar_to_blogtemplate.
Integration with Claude Desktop
To use this server with Claude for Desktop:
-
Open your Claude Desktop configuration file:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
-
Add the server configuration. You can copy the content from
claude_desktop_config.jsonin this directory:{ "mcpServers": { "calculator": { "command": "uv", "args": [ "--directory", "C:\\Users\\Your_Name\\Desktop\\mcps\\calculator_server", "run", "server.py" ] } } }Important: Make sure the path in
--directorymatches the actual absolute path to yourcalculator_serverfolder. -
Restart Claude for Desktop.
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。