### Start OpenMemory Frontend

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/tw/openmemory-mcp.md

Copy the example environment file for the UI and start the frontend services.

```bash
cp ui/.env.example ui/.env
make ui
```

--------------------------------

### MCP Server Startup Output Example

Source: https://github.com/cnych/claude-mcp/blob/main/public/docs/zh/mcp-py-sdk-deep.md

Example output when starting an MCP server with Streamable HTTP transport. It shows the server address, supported tools, and Uvicorn process information.

```bash
$ python main.py
🌤️ 启动产品 MCP 服务器...
📍 支持的功能:
  - 获取产品列表 (get_products)
  - 获取库存列表 (get_inventory)
  - 获取订单列表 (get_orders)
  - 创建采购订单 (create_purchase)

INFO:     Started server process [26897]
INFO:     Waiting for application startup.
[06/05/25 16:39:19] INFO     StreamableHTTP session manager started  streamable_http_manager.py:109
INFO:     Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:8083 (Press CTRL+C to quit)
```

--------------------------------

### Local Development Setup and Run Commands

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/debugg-ai-mcp.md

These bash commands guide you through setting up the DebuggAI MCP server locally. It includes installing dependencies, copying a configuration file, and launching the MCP server with the specified configuration.

```bash
# Clone the repo and install dependencies
npm install

# Copy the test config and insert your creds
cp test-config-example.json test-config.json

# Run the MCP server locally
npx @modelcontextprotocol/inspector --config debugg-ai-mcp/test-config.json --server debugg-ai-mcp
```

--------------------------------

### Run Stdio Client Example

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/apify-mcp.md

Execute the example stdio client script to interact with the MCP server. This script demonstrates starting the server with specified Actors, connecting, listing tools, and calling a tool.

```bash
node dist/examples/clientStdio.js
```

--------------------------------

### Start Exploring Example

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/cascade-thinking-mcp.md

Example of initiating a thinking process with the Cascade Thinking MCP Server.

```APIDOC
## Example: Start Exploring

```json
{
  "thought": "Analyzing authentication options for our API",
  "thoughtNumber": "S1",
  "totalThoughts": 3,
  "nextThoughtNeeded": true
}
```
```

--------------------------------

### Install and Run OpenMemory MCP Server

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/zh/openmemory-mcp.md

Steps to clone the repository, set up environment variables, build the Docker image, and launch the API, vector database, and MCP services. Also includes instructions for starting the frontend interface.

```bash
git clone <https://github.com/mem0ai/mem0.git>
cd openmemory
cd api
touch .env
echo "OPENAI_API_KEY=your_key_here" > .env
cd ..
make build
make up
cp ui/.env.example ui/.env
make ui
```

--------------------------------

### Example Server Interaction and Output

Source: https://github.com/cnych/claude-mcp/blob/main/public/docs/en/write-ts-client.md

This example shows the client output when querying for weather information. It includes the server's confirmation, connected tools, client start message, and the tool call with arguments and the final weather forecast.

```bash
node build/index.js /Users/cnych/src/weather-server/build/index.js
# output
Weather MCP server running on stdio
Connected to server with tools: [ 'get_forecast' ]

MCP Client Started!
Type your queries or 'exit' to exit.

Query: Beijing weather for the next 3 days

I can get the weather forecast for Beijing for the next 3 days. Let me do that for you now.
[Calling tool get_forecast with args {"city":"Beijing","days":3}]
# Beijing Weather Forecast

## Next 3 Days:
- **March 24, 2025**: 21°C with overcast clouds
- **March 25, 2025**: 21°C with scattered clouds
- **March 26, 2025**: 20°C with overcast clouds

The temperature will remain relatively stable around 20-21°C over the next three days, with cloudy conditions throughout. March 25th will have partially clear skies with scattered clouds, while the other days will be predominantly overcast.

Query:
```

--------------------------------

### Install talk-to-pc-mcp from Source

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/talk-to-pc-mcpserver.md

Install the MCP server by cloning the repository and installing it locally. This method is useful for development or if you need the latest changes.

```bash
git clone https://github.com/Irene-123/talk-to-your-pc-mcp-server.git
cd talk-to-your-pc-mcp-server
pip install -e .
```

--------------------------------

### Install from Source

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/deepwiki-mcp.md

Steps to clone the repository, install dependencies, and build the package from source.

```bash
# Clone the repository
git clone https://github.com/regenrek/mcp-deepwiki.git
cd mcp-deepwiki

# Install dependencies
npm install

# Build the package
npm run build
```

--------------------------------

### Install and Test mcp-feedback-enhanced

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/mcp-feedback-enhanced.md

Installs the tool using uv and performs a quick test. Ensure uv is installed first.

```bash
pip install uv

uvx mcp-feedback-enhanced@latest test
```

--------------------------------

### Install Development Dependencies

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/keboola-mcp.md

Installs basic development dependencies using uv. Use the recommended setup for IDE integration and testing packages.

```bash
uv sync --extra dev
```

```bash
uv sync --extra dev --extra tests --extra integtests --extra codestyle
```

--------------------------------

### Setup Python Virtual Environment (Linux/MacOS)

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/comidp-mcp-server.md

Creates and activates a Python virtual environment on Linux or MacOS. Installs project dependencies from requirements.txt.

```bash
cd comidp-mcp/src
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
```

--------------------------------

### Setup Python Virtual Environment (Windows)

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/comidp-mcp-server.md

Creates and activates a Python virtual environment on Windows. Installs project dependencies from requirements.txt.

```bash
cd comidp-mcp\src
python -m venv .venv
.venv\Scripts\activate
pip install -r requirements.txt
```

--------------------------------

### Install Prerequisites with uv

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/browser-use-mcp-server.md

Installs uv, mcp-proxy, and updates the shell environment.

```bash
curl -LsSf https://astral.sh/uv/install.sh | sh
uv tool install mcp-proxy
uv tool update-shell
```

--------------------------------

### Start OpenMemory Services and Frontend

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/openmemory-mcp.md

Commands to start all OpenMemory services, including the API server, vector database, and MCP server components, followed by starting the frontend.

```bash
# Start all services (API server, vector database, and MCP server components)
make up

# Start the frontend
cp ui/.env.example ui/.env
make ui
```

--------------------------------

### Generate UI Component with CLI

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/zh/magic-mcp.md

Use the CLI to install and configure the Magic MCP client with your API key. This command automates the setup process for supported IDEs.

```bash
npx @21st-dev/cli@latest install <客户端> --api-key <密钥>
```

--------------------------------

### Manual Installation and Build

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/snowflake.md

Steps to manually install the Snowflake MCP Server by cloning the repository, installing dependencies, building the server, and configuring environment variables.

```bash
git clone https://github.com/patrickfreyer/mcp-server-snowflake.git
cd mcp-server-snowflake

npm install

npm run build

cp .env.example .env
# Edit .env with your Snowflake credentials
```

--------------------------------

### Install LangChain MCP Adapters

Source: https://github.com/cnych/claude-mcp/blob/main/public/blogs/en/langchain-mcp-adapters.md

Install the library using pip. If using uv, use `uv add`.

```bash
pip install langchain-mcp-adapters
```

```bash
uv add langchain-mcp-adapters langgraph langchain-openai
```

--------------------------------

### Install Dependencies

Source: https://github.com/cnych/claude-mcp/blob/main/public/clients/en/apify-client.md

Run this command after cloning the repository to install all necessary Node.js packages for the client.

```shell
npm install
```

--------------------------------

### Install FastMCP

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/backlinks-mcp.md

Install the FastMCP library after cloning the repository.

```bash
uv pip install fastmcp
```

--------------------------------

### Install mcp-server-fetch with Pip

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/fetch.md

Install the fetch server package using pip. This is an alternative to using uv.

```bash
pip install mcp-server-fetch
```

--------------------------------

### Install SEO MCP Dependencies (Manual)

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/seo-mcp.md

Install SEO MCP dependencies after cloning the repository using pip or uv.

```bash
pip install -e .
# or
uv pip install -e .
```

--------------------------------

### Install Dependencies and Build Project

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/firecrawl-mcp.md

Commands to install project dependencies using npm and then build the project.

```bash
# Install dependencies
npm install

# Build
npm run build
```

--------------------------------

### Install talk-to-pc-mcp via PyPI

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/talk-to-pc-mcpserver.md

Use this command to install the recommended version of the MCP server from PyPI.

```bash
pip install talk-to-pc-mcp==0.1.1
```

--------------------------------

### Install Project Dependencies

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/interactive-feedback-mcp.md

Install all project dependencies using uv. This command also creates a virtual environment for the project.

```shell
uv sync
```

--------------------------------

### Clone Perplexity Ask MCP Server Repository

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/perplexity-ask-mcp-server.md

Clone the modelcontextprotocol repository to get started with the perplexity-ask server. Navigate to the directory and install dependencies.

```bash
git clone git@github.com:ppl-ai/modelcontextprotocol.git
cd modelcontextprotocol/perplexity-ask && npm install
```

--------------------------------

### Initialize npm Project

Source: https://github.com/cnych/claude-mcp/blob/main/public/docs/en/write-ts-client.md

Create a new project directory and initialize an npm project. This is the first step in setting up your client.

```bash
mkdir mcpclient-demo
cd mcpclient-demo
npm init -y
```

--------------------------------

### Install Prerequisites with winget (Windows)

Source: https://github.com/cnych/claude-mcp/blob/main/public/docs/en/quickstart.md

Installs uv, git, and sqlite3 using winget. Alternatively, download directly from their respective websites.

```bash
# Using winget
winget install --id=astral-sh.uv -e
winget install git.git sqlite.sqlite

# Or download directly:
# uv: https://docs.astral.sh/uv/
# Git: https://git-scm.com
# SQLite: https://www.sqlite.org/download.html
```

--------------------------------

### MCP Prompt Get Request and Response Example

Source: https://github.com/cnych/claude-mcp/blob/main/public/docs/en/write-ts-server.md

Shows the JSON request to retrieve detailed information for a specific prompt, including parameters, and an example response with messages.

```json
// Request
{
  "method": "prompts/get",
  "params": {
    "name": "analyze-code",
    "arguments": {
      "language": "python"
    }
  }
}

// Response
{
  "description": "Analyze Python code for potential improvements",
  "messages": [
    {
      "role": "user",
      "content": {
        "type": "text",
        "text": "Please analyze the following Python code for potential improvements:\n\n```python\ndef calculate_sum(numbers):\n    total = 0\n    for num in numbers:\n        total = total + num\n    return total\n\nresult = calculate_sum([1, 2, 3, 4, 5])\nprint(result)\n```"
      }
    }
  ]
}
```

--------------------------------

### Start Development Server

Source: https://github.com/cnych/claude-mcp/blob/main/README.md

Start the development server using npm or yarn. Open http://localhost:3000 in your browser to view the site.

```bash
npm run dev
```

```bash
yarn dev
```

--------------------------------

### Install iTerm MCP Server via Smithery CLI

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/iterm-mcp.md

Use the Smithery CLI to automatically install the iTerm MCP server for Claude Desktop. This command simplifies the setup process.

```bash
npx -y @smithery/cli install iterm-mcp --client claude
```

--------------------------------

### Start OpenMemory Services

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/tw/openmemory-mcp.md

Start all necessary services including the API server, vector database, and MCP server components using the make command.

```bash
make up
```

--------------------------------

### Initialize Project with uv

Source: https://github.com/cnych/claude-mcp/blob/main/public/docs/en/mcp-py-sdk-deep.md

Use 'uv init' to create a new Python project and 'uv add' to include necessary dependencies like FastAPI and Uvicorn.

```bash
uv init product-mcp --python 3.13
cd product-mcp
uv add fastapi uvicorn
```

--------------------------------

### Start MCP Inspector for NPM Packages

Source: https://github.com/cnych/claude-mcp/blob/main/public/docs/en/write-ts-server.md

Use `npx -y` to start the MCP Inspector for server packages installed via NPM. This command ensures the inspector is available and then launches the specified package with its arguments.

```bash
npx -y @modelcontextprotocol/inspector npx <package-name> <args>
# For example
npx -y @modelcontextprotocol/inspector npx server-postgres postgres://127.0.0.1/testdb
```

--------------------------------

### Build and Run Local Server

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/mcp-chart-server.md

Build the project and start the local Chart MCP server.

```bash
npm run build
npm start
```

--------------------------------

### Get Backlink List API Call

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/seo-mcp.md

Example of how to call the get_backlinks_list API to retrieve backlink data for a specified domain.

```python
get_backlinks_list(domain: str)
```

--------------------------------

### Get Notion Page Content by ID

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/notion-mcp-server.md

Example command to retrieve the content of a Notion page using its unique ID.

```plaintext
Get the content of page 1a6b35e6e67f802fa7e1d27686f017f2
```

--------------------------------

### Clone Repository and Setup Environment

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/tw/openmemory-mcp.md

Clone the OpenMemory repository, navigate to the directory, set up the .env file with your OpenAI API key, and build the Docker images.

```bash
git clone <https://github.com/mem0ai/mem0.git>
cd openmemory

cd api
touch .env
echo "OPENAI_API_KEY=your_key_here" > .env

cd ..
make build
```

--------------------------------

### Developer Installation of mcp-feedback-enhanced

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/mcp-feedback-enhanced.md

Steps to clone the repository, navigate to the directory, and synchronize dependencies using uv for local development.

```bash
git clone https://github.com/Minidoracat/mcp-feedback-enhanced.git
cd mcp-feedback-enhanced
uv sync
```

--------------------------------

### Keyword Generator API Call

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/seo-mcp.md

Example of how to call the keyword_generator API to get keyword ideas and SEO suggestions for a given keyword, country, and search engine.

```python
keyword_generator(keyword: str, country: str = "us", search_engine: str = "Google")
```

--------------------------------

### Configure VS Code MCP Server

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/apify-mcp.md

Add this JSON to your VS Code User Settings to manually install the Apify MCP Server. The `APIFY_TOKEN` will be prompted for when the server starts.

```json
{
  "mcp": {
    "inputs": [
      {
        "type": "promptString",
        "id": "apify_token",
        "description": "Apify API Token",
        "password": true
      }
    ],
    "servers": {
      "actors-mcp-server": {
        "command": "npx",
        "args": ["-y", "@apify/actors-mcp-server"],
        "env": {
          "APIFY_TOKEN": "${input:apify_token}"
        }
      }
    }
  }
}
```

--------------------------------

### Install Prerequisites with Homebrew (macOS)

Source: https://github.com/cnych/claude-mcp/blob/main/public/docs/en/quickstart.md

Installs uv, git, and sqlite3 using Homebrew. Alternatively, download directly from their respective websites.

```bash
# Using Homebrew
brew install uv git sqlite3

# Or download directly:
# uv: https://docs.astral.sh/uv/
# Git: https://git-scm.com
# SQLite: https://www.sqlite.org/download.html
```

--------------------------------

### Server-side Handler for Getting Prompt Details (TypeScript)

Source: https://github.com/cnych/claude-mcp/blob/main/public/docs/en/write-ts-server.md

Registers a request handler for the `prompts/get` endpoint using TypeScript. This example handles the 'summarize_notes' prompt by embedding note content as resources.

```typescript
/**
 * Handler for summarizing all notes.
 * Returns a prompt for requesting to summarize all notes, and embeds the note content as resources.
 */
server.setRequestHandler(GetPromptRequestSchema, async (request) => {
  if (request.params.name !== "summarize_notes") {
    throw new Error("Unknown prompt");
  }

  const embeddedNotes = Object.entries(notes).map(([id, note]) => ({
    type: "resource" as const,
    resource: {
      uri: `note:///${id}`,
      mimeType: "text/plain",
      text: note.content,
    },
  }));

  return {
    messages: [
      {
        role: "user",
        content: {
          type: "text",
          text: "Please summarize the following notes:",
        },
      },
      ...embeddedNotes.map((note) => ({
        role: "user" as const,
        content: note,
      })),
      {
        role: "user",
        content: {
          type: "text",
          text: "Provide a concise summary of all the notes above.",
        },
      },
    ],
  };
});
```

--------------------------------

### Fetch Tool

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/fetch.md

The `fetch` tool allows you to retrieve content from a given URL. You can specify parameters to control the length of the content, the starting index for extraction, and whether to get raw content or markdown-converted content.

```APIDOC
## fetch

### Description
Fetches a URL from the internet and extracts its contents as markdown.

### Parameters
#### Query Parameters
- **url** (string, required) - URL to fetch
- **max_length** (integer, optional) - Maximum number of characters to return (default: 5000)
- **start_index** (integer, optional) - Start content from this character index (default: 0)
- **raw** (boolean, optional) - Get raw content without markdown conversion (default: false)
```

--------------------------------

### Local Development Installation for MCPQL

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/mssqlserver.md

Steps to clone, install dependencies, build the project, and configure database connection using a .env file for local development of the MCPQL server.

```bash
git clone https://github.com/hendrickcastro/MCPQL.git
cd MCPQL
npm install
npm run build
```

--------------------------------

### MCP Documentation File Front Matter and Configuration

Source: https://context7.com/cnych/claude-mcp/llms.txt

Example of an MCP documentation file's Markdown content, showing YAML front matter for metadata and a JSON block for quick start configuration.

```markdown
---
title: Quick Start
description: How to quickly get started with Claude MCP
section: getting_started
prev: protocol
next: write-ts-server
pubDate: 2024-12-02
order: 4
---

# Quick Start

Connect Claude Desktop to a local SQLite database:

```json
{
  "mcpServers": {
    "sqlite": {
      "command": "uvx",
      "args": ["mcp-server-sqlite", "--db-path", "/Users/YOUR_USERNAME/test.db"]
    }
  }
}
```
```

--------------------------------

### Prompt: Start Screen Recording

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/zh/ios-simulator-mcp.md

Use this prompt to start recording the simulator screen. The video is typically saved to `~/Downloads/simulator_recording_$DATE.mp4` by default.

```plaintext
开始录制模拟器屏幕视频（默认保存到~/Downloads/simulator_recording_$DATE.mp4）
```

--------------------------------

### Local Development Installation Commands

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/cosmosdb-sql.md

Steps to clone the repository, install dependencies, and build the project for local development. This is an alternative to using npx directly from GitHub.

```bash
git clone <your-repo-url>
cd MCPCosmosDB
npm install
npm run build
```

--------------------------------

### Install Firecrawl MCP Globally

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/firecrawl-mcp.md

Installs the Firecrawl MCP server globally using npm. This command is for manual installation.

```bash
npm install -g firecrawl-mcp
```

--------------------------------

### Install uv with pip

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/comidp-mcp-server.md

Installs the 'uv' package manager using pip. Ensure Python 3.10 or higher is installed.

```bash
pip install uv 
```

--------------------------------

### Install Python Dependencies

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/zh/image-gen-server.md

Install the required Python dependencies for the Image-Gen-Server using pip and uv. Ensure you have Python 3.10+ installed.

```bash
pip install -r requirements.txt
pip install uv
```

--------------------------------

### Client Interaction Example

Source: https://github.com/cnych/claude-mcp/blob/main/public/docs/en/mcp-py-sdk-basic.md

This bash command demonstrates the execution of a simple client script that loads MCP server configurations, fetches tools, and initiates an interactive session with the user.

```bash
$ python simple_client.py
✓ Loaded 1 MCP server configuration

→ Fetching list of available tools...
→ Connecting to server: weather
[05/25/25 11:42:51] INFO     Processing request of type ListToolsRequest  server.py:551
✓ weather: 2 tools
                              Available MCP Tools
┏━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ Server  ┃ Tool Name            ┃ Description                          ┃
┡━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩
│ weather │ get_current_weather  │                                      │
│         │                      │ Fetch current weather for a city     │
│         │                      │                                      │
│         │                      │ Args:                                │
│         │                      │     city: City name (English)        │
│         │                      │                                      │
│         │                      │ Returns:                             │
│         │                      │     Formatted current weather info   │
│         │                      │                                      │
│         │ get_weather_forecast │                                      │
│         │                      │ Fetch weather forecast for a city    │
│         │                      │                                      │
│         │                      │ Args:                                │
│         │                      │     city: City name (English)        │
│         │                      │     days: Forecast days (1-5, default 5)│
│         │                      │                                      │
│         │                      │ Returns:                             │
│         │                      │     Formatted weather forecast info  │
│         │                      │                                      │
└─────────┴──────────────────────┴──────────────────────────────────────┘
╭────────────── Welcome to MCP Client ──────────────╮
│ MyMCP Client Started                              │
│ Enter your questions, and I'll use available MCP tools to help. │
│ Type 'tools' to see available tools               │
│ Type 'exit' or 'quit' to exit.                    │
╰─────────────────────────────────────────────────╯

You: Hello, who are you?
⠹ Thinking...

Assistant:
╭──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Hello! I'm an intelligent assistant who can help you with various tasks, like answering questions, checking the weather, providing suggestions, and more. Feel free to ask me anything! 😊 │

```

--------------------------------

### Install SEO MCP using uv

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/seo-mcp.md

Install the seo-mcp package using uv. Ensure Python 3.10 or higher is installed.

```bash
uv pip install seo-mcp
```

--------------------------------

### Call a Tool with Server Parameters

Source: https://github.com/cnych/claude-mcp/blob/main/public/docs/en/mcp-py-sdk-basic.md

Demonstrates how to call a specific tool on a server using prepared server parameters. It includes environment variable preparation and uses async context managers for client sessions.

```python
async def call_tool(self, server_name: str, tool_name: str, arguments: Dict[str, Any]) -> Any:
        """Call the specified tool"""
        config = self.servers.get(server_name)
        if not config:
            raise ValueError(f"Server {server_name} does not exist")

        try:
            # Prepare environment variables
            env = os.environ.copy()
            if config.env:
                env.update(config.env)

            # Create server parameters
            server_params = StdioServerParameters(
                command=config.command,
                args=config.args,
                env=env
            )

            # Use async with context manager (nested)
            async with stdio_client(server_params) as (read, write):
                async with ClientSession(read, write) as session:
                    await session.initialize()

                    # Call tool
                    result = await session.call_tool(tool_name, arguments)
                    return result

        except Exception as e:
            console.print(f"[red]✗ Failed to call tool {tool_name}: {e}[/red]")
            raise
```

--------------------------------

### Configure Environment Variables

Source: https://github.com/cnych/claude-mcp/blob/main/public/clients/en/apify-client.md

Create a .env file and add your API tokens. Refer to .env.example for a full list of available settings.

```plaintext
APIFY_TOKEN=YOUR_APIFY_TOKEN
LLM_PROVIDER_API_KEY=YOUR_API_KEY
```

--------------------------------

### Install SEO MCP using pip

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/seo-mcp.md

Install the seo-mcp package using pip. Ensure Python 3.10 or higher is installed.

```bash
pip install seo-mcp
```

--------------------------------

### Install uv Package Manager

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/interactive-feedback-mcp.md

Install the uv Python package manager using pip. This is a prerequisite for installing project dependencies.

```shell
pip install uv
```

--------------------------------

### Set up Winston AI MCP Server Locally

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/winston-ai-mcp.md

Clone the repository, install dependencies, and run the MCP server locally. A .env file is required for your API key.

```env
WINSTONAI_API_KEY=your_actual_api_key_here
```

```bash
# Clone the repository
git clone https://github.com/gowinston-ai/winston-ai-mcp-server.git
cd winston-ai-mcp-server

# Install dependencies
npm install

# Build the project and start the server
npm run mcp-start
```

--------------------------------

### Initialize uv Project

Source: https://github.com/cnych/claude-mcp/blob/main/public/docs/en/mcp-py-sdk-basic.md

Initialize a new project managed by uv and specify the Python version. Navigate into the created directory.

```bash
uv init mcp-server-weather --python 3.13 # Specify the version
cd mcp-server-weather
```

--------------------------------

### Install uv with PowerShell (Windows)

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/keboola-mcp.md

Installs the 'uv' package manager on Windows using PowerShell. This method uses the official installer script.

```powershell
# Using the installer script
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

# Or using pip
pip install uv

# Or using winget
winget install --id=astral-sh.uv -e
```

--------------------------------

### Install uv with Homebrew (macOS/Linux)

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/keboola-mcp.md

Installs the 'uv' package manager using Homebrew on macOS or Linux systems. Ensure Homebrew is installed first.

```bash
#if homebrew is not installed on your machine use:
# /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"

# Install using Homebrew
brew install uv
```

--------------------------------

### Clone and Install Excel MCP Server

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/excel-mcp-server.md

Clone the repository and install the server dependencies using uv. Ensure Python 3.10 or higher is installed.

```bash
git clone https://github.com/haris-musa/excel-mcp-server.git
cd excel-mcp-server
```

```bash
uv pip install -e .
```

--------------------------------

### Install Build Tools with npm

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/MCPControl.md

Installs necessary build tools for the project using npm. Ensure Node.js 18 or later is installed first.

```bash
npm install -g node-gyp
npm install -g cmake-js
```

--------------------------------

### Initialize Project with MCP Server

Source: https://github.com/cnych/claude-mcp/blob/main/public/docs/en/streamable-http.md

Use this command to create a new project for an MCP server. Ensure you are in the project root directory afterward to update dependencies.

```bash
npx @modelcontextprotocol/create-server streamable-demo
```

--------------------------------

### Run SSE Client Example

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/apify-mcp.md

Execute the example SSE client script to test the server with Server-Sent Events transport. Note that you may need to change the local server URL in the script.

```bash
node dist/examples/clientSse.js
```

--------------------------------

### Clone Repository and Navigate

Source: https://github.com/cnych/claude-mcp/blob/main/README.md

Use these bash commands to clone the repository and navigate into the project directory.

```bash
git clone https://github.com/cnych/claude-mcp.git
cd claude-mcp
```

--------------------------------

### Install Dependencies

Source: https://github.com/cnych/claude-mcp/blob/main/README.md

Install project dependencies using npm or yarn.

```bash
npm install
```

```bash
yarn install
```

--------------------------------

### Get All Webhooks

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/viso-trust-mcp.md

Get all webhooks. Returns a list of all webhook configurations.

```APIDOC
## get_all_webhooks - Get all webhooks

### Description
Returns a list of all webhook configurations.

### Parameters
No parameters required.
```

--------------------------------

### Initialize Response Example

Source: https://github.com/cnych/claude-mcp/blob/main/public/docs/en/protocol.md

The server responds to the initialize request, confirming the protocol version and detailing its own capabilities and server information.

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "protocolVersion": "2024-11-05",
    "capabilities": {
      "logging": {},
      "prompts": {
        "listChanged": true
      },
      "resources": {
        "subscribe": true,
        "listChanged": true
      },
      "tools": {
        "listChanged": true
      }
    },
    "serverInfo": {
      "name": "ExampleServer",
      "version": "1.0.0"
    }
  }
}
```

--------------------------------

### Example Usage of the Search Tool

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/web-search.md

Demonstrates how to invoke the 'search' tool through the MCP server. Specify the server name, tool name, and arguments.

```typescript
use_mcp_tool({
  server_name: "web-search",
  tool_name: "search",
  arguments: {
    query: "your search query",
    limit: 3, // optional
  },
});
```

--------------------------------

### Install SEO MCP Dependencies for Development

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/seo-mcp.md

Install development dependencies for the SEO MCP project after cloning the repository. This command ensures all necessary packages are installed in editable mode.

```bash
git clone https://github.com/cnych/seo-mcp.git
cd seo-mcp
uv sync  # or use pip install -e .
```

--------------------------------

### Example client config for uv

Source: https://github.com/cnych/claude-mcp/blob/main/public/servers/en/dify-mcp-server.md

An example client configuration for running the Dify MCP Server using 'uv'. Ensure the paths for the server directory and config file are correct.

```json
{
  "mcpServers": {
    "dify-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "/Users/lyx/Downloads/dify-mcp-server",
        "run",
        "dify_mcp_server"
      ],
      "env": {
        "CONFIG_PATH": "/Users/lyx/Downloads/config.yaml"
      }
    }
  }
}
```