Anchor MCP

🚀 Protection Program MCP

This is an MCP CLI server template for Anchor programs. The Model Context Protocol (MCP) is an open protocol designed to enable seamless integration between large language model applications and external data sources and tools. Whether you're building an AI-driven IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standard way to connect LLMs with their required context. This server is based on mcp-rs-template.

🚀 Quick Start

✨ Features

• The Model Context Protocol (MCP) is an open protocol for seamless integration between large language model applications and external data sources and tools.
• This server is based on mcp-rs-template.

📦 Installation

Not provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

CLI Options

• --mcp: Enable the MCP server.
• --prompts: Display prompts.
• --tools: Display tools.

Advanced Usage

How to use the Anchor MCP CLI server in Claude Desktop?

1. Edit claude_desktop_config.json: Open Claude Desktop -> Settings -> Developer -> Edit Configuration.
2. Add the following configuration to the servers section:

{
   "mcpServers": {
      "security_check_program": {
         "command": "security_check_program",
         "args": [
            "--mcp"
         ]
      },
      "security_check_file": {
         "command": "security_check_file",
         "args": [
            "--mcp"
         ]
      }
   }
}

If you want to check the MCP logs, use tail -n 20 -f ~/Library/Logs/Claude/mcp*.log.

📚 Documentation

References

• Solana Fender: https://github.com/honey-guard/solana-fender
• mcp-rs-tempalte: https://github.com/linux-china/mcp-rs-template

📄 License

This project is licensed under the GPL v3 License.