Anthropic Prompt MCP

🚀 MCP Anthropic Server (mcp-anthropic)

A Model Context Protocol (MCP) server that provides tools for interacting with Anthropic's experimental prompt engineering API.

🚀 Quick Start

The MCP Anthropic Server offers a set of tools to interact with Anthropic's experimental prompt engineering API. It simplifies the process of generating, improving, and templatizing prompts.

✨ Features

The server provides the following tools:

• generate_prompt: Generate a prompt based on a task description.
• improve_prompt: Improve an existing prompt based on feedback.
• templatize_prompt: Convert a specific prompt example into a reusable template.

📦 Installation

1. Clone the repository (if applicable)
2. Navigate to the project directory:

   cd mcp-anthropic
   

3. Install dependencies:

   npm install
   

4. Configure the API key:
   • Create a .env file in the project root directory (./mcp-anthropic/.env).
   • Add your Anthropic API key to the .env file:

     ANTHROPIC_KEY=your_anthropic_api_key_here
     

   • Ensure this file is not committed to version control (it should be covered by .gitignore).
   • Note for LibreChat integration: For specific instructions on setting up and running this server as a subprocess in LibreChat (including API key handling), refer to the documentation.md file.

💻 Usage Examples

Starting the Server

1. Build the TypeScript code:

   npm run build
   

2. Start the server:

   npm start
   

   The server will start listening for MCP connections. You should see output indicating that the server has started and the tools have been registered.

📚 Documentation

generate_prompt

Generate a prompt based on a task description.

Input Schema:

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task description for which the prompt should be designed (e.g., 'A chef for a meal planning service')"
    },
    "target_model": {
      "type": "string",
      "description": "Target Anthropic model identifier (e.g., 'claude-3-opus-20240229')"
    }
  },
  "required": ["task", "target_model"]
}

improve_prompt

Improve an existing prompt based on feedback.

Input Schema:

{
  "type": "object",
  "properties": {
    "messages": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "role": { "type": "string", "description": "Role (e.g., 'user', 'assistant')" },
          "content": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "type": { "type": "string", "description": "Content type" },
                "text": { "type": "string", "description": "Text content" }
              },
              "required": ["type", "text"]
            },
            "description": "Content block"
          }
        },
        "required": ["role", "content"]
      },
      "description": "Sequence representing a prompt conversation"
    },
    "system": {
      "type": "string",
      "description": "(Optional) System prompt associated with the example."
    }
  },
  "required": ["messages"]
}

templatize_prompt

Convert a specific prompt example into a reusable template.

Input Schema:

{
  "type": "object",
  "properties": {
    "messages": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "role": { "type": "string", "description": "Role (e.g., 'user', 'assistant')" },
          "content": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "type": { "type": "string", "description": "Content type" },
                "text": { "type": "string", "description": "Text content" }
              },
              "required": ["type", "text"]
            },
            "description": "Content block"
          }
        },
        "required": ["role", "content"]
      },
      "description": "Sequence representing an example prompt conversation"
    },
    "system": {
      "type": "string",
      "description": "(Optional) System prompt associated with the example."
    }
  },
  "required": ["messages"]
}