Peacock MCP Server

What does “Peacock” MCP Server do?

The Peacock MCP Server is designed to serve as a Model Context Protocol (MCP) server for the Peacock extension in Visual Studio Code. Its primary purpose is to illustrate how an MCP server can facilitate connections between AI assistants and external APIs, thereby enhancing development workflows. By acting as a bridge, the Peacock MCP Server enables AI-powered assistants to interact programmatically with the VS Code environment, such as customizing editor appearance or managing project-specific settings. This empowers developers to automate tasks like theming, workspace identification, or other API-driven interactions, ultimately streamlining and enriching the coding experience.

List of Prompts

No prompt templates are explicitly mentioned in the available documentation or repository files.

List of Resources

No explicit resources are described in the available documentation or repository files.

List of Tools

No explicit tools are listed in the available documentation or repository files, and server.py is not present in this repository.

Use Cases of this MCP Server

• API Interaction Demonstration: The Peacock MCP Server is primarily intended to showcase how MCP servers can be used to interact with APIs. This can help developers understand best practices for integrating AI assistants with various services.
• VS Code Extension Enhancement: By connecting to Peacock via MCP, developers can automate theme and appearance adjustments across VS Code workspaces, improving team workflows and workspace identification.
• Developer Workflow Automation: The server can serve as a basis for automating repetitive tasks, such as switching editor colors based on project context or CI/CD status, thereby reducing manual configuration.
• Educational Purposes: The repository is a valuable resource for those learning how to implement MCP servers to connect AI tools with external APIs or systems.
• Template for Custom MCP Servers: Developers can use this as a template to create their own MCP servers for other extensions or applications that require interaction between AI and APIs.

How to set it up

Windsurf

1. Ensure Node.js is installed on your system.
2. Locate Windsurf’s configuration file (usually wind.config.json).
3. Add the Peacock MCP Server entry using a JSON snippet:

   {
     "mcpServers": {
       "peacock-mcp": {
         "command": "npx",
         "args": ["@johnpapa/peacock-mcp@latest"]
       }
     }
   }
   

4. Save the configuration file and restart Windsurf.
5. Verify the setup by checking if Windsurf recognizes the Peacock MCP server.

Claude

1. Make sure Node.js is available.
2. Open Claude’s MCP server configuration (e.g., claude.json).
3. Add:

   {
     "mcpServers": {
       "peacock-mcp": {
         "command": "npx",
         "args": ["@johnpapa/peacock-mcp@latest"]
       }
     }
   }
   

4. Save and restart Claude.
5. Confirm the Peacock MCP server is listed in Claude’s UI.

Cursor

1. Install Node.js.
2. Open Cursor’s cursor.config.json.
3. Insert:

   {
     "mcpServers": {
       "peacock-mcp": {
         "command": "npx",
         "args": ["@johnpapa/peacock-mcp@latest"]
       }
     }
   }
   

4. Save file, restart Cursor.
5. Test by invoking a command that uses the MCP server.

Cline

1. Ensure Node.js is installed.
2. Edit or create Cline’s configuration file (e.g., cline.config.json).
3. Add the MCP server:

   {
     "mcpServers": {
       "peacock-mcp": {
         "command": "npx",
         "args": ["@johnpapa/peacock-mcp@latest"]
       }
     }
   }
   

4. Save and restart Cline.
5. Check for successful MCP server registration.

Securing API Keys

Store API keys as environment variables and reference them in your configuration. Example:

{
  "mcpServers": {
    "peacock-mcp": {
      "command": "npx",
      "args": ["@johnpapa/peacock-mcp@latest"],
      "env": {
        "API_KEY": "${PEACOCK_API_KEY}"
      },
      "inputs": {
        "apiKey": "${PEACOCK_API_KEY}"
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "peacock-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “peacock-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the tables, the Peacock MCP server serves as a helpful demonstration project but lacks detailed documentation, prompt templates, resources, and tool definitions, limiting its practical use for advanced MCP integrations. Its main value is as a learning or starting point for MCP server development.

MCP Score

Overall rating: 3/10 – This MCP server is a useful reference for getting started but is quite limited in scope and documentation for real-world use.