Calva MCP Server

🚀 Making Co Make Co Make Co Make

This project implements a server named Calva MCP Server, which uses the Model Context Protocol (MCP) to create a bridge between AI assistants and your REPL. Through this server, AI assistants can execute code and receive real-time feedback, enabling them to better understand the actual behavior of the code and the shape of the data.

🚀 Quick Start

Project Goals

• When an AI assistant needs a deeper understanding of your code, it can execute it in your REPL.
• The execution results are returned to the AI assistant, allowing it to understand the actual data shapes and function behaviors.
• This interaction forms a powerful feedback loop that continuously optimizes the suggestions.
• Users always have control over this process and benefit from an AI partner that truly understands the running code.

Project Architecture

flowchart TD
    subgraph 互动程序员["Interactive Programmers"]
        User([You])
        AIAgent([AI Assistant])
        User <--> AIAgent
    end

    subgraph VS Code["VS Code"]

        MCP["Calva MCP Server"]

        subgraph Calva["Calva"]
            REPLClient["REPL Client"]
        end

        subgraph 项目["Clojure Project"]

            subgraph 运行应用程序["Running Application"]
                SourceCode["Source Code"]
                REPL["REPL"]
            end
        end
    end

    User --> SourceCode
    User --> Calva
    REPLClient --> REPL
    AIAgent --> SourceCode
    AIAgent --> MCP
    MCP --> Calva

    classDef users fill:#ffffff,stroke:#63b132,stroke-width:1px,color:#63b132;
    classDef programmers fill:#63b132,stroke:#000000,stroke-width:2px,color:#ffffff;
    classDef vscode fill:#0078d7,stroke:#000000,stroke-width:1px,color:#ffffff;
    classDef calva fill:#df793b,stroke:#ffffff,stroke-width:1px,color:#ffffff;
    classDef highlight fill:#ffffff,stroke:#000000,stroke-width:1px,color:#000000;
    classDef dark fill:#333333,stroke:#ffffff,stroke-width:1px,color:#ffffff;
    classDef repl fill:#5881d8,stroke:#ffffff,stroke-width:1px,color:#ffffff;
    classDef running fill:#63b132,stroke:#ffffff,stroke-width:1px,color:#ffffff;
    classDef project fill:#888888,stroke:#ffffff,stroke-width:1px,color:#ffffff;

    class User,AIAgent users;
    class VS Code vscode;
    class Calva,MCP calva;
    class REPLClient repl;
    class 项目 project;
    class SourceCode dark;
    class 运行应用程序 running;
    class REPL repl;
    class 互动程序员 programmers;

Usage Steps

1. Connect Calva to your Clojure/ClojureScript project.
2. Execute the command: Calva MCP Server: Start Socket Server.
3. In the .vscode/mcp.json file, use the Start button to start the "calva" server.
4. If you want the AI assistant to have full REPL permissions, enable the relevant option in the settings.
5. Now, the AI assistant can execute code and receive real-time feedback.

✨ Features

• Technology Stack: Built on Clojure and VS Code extensions.
• Function Highlights: Supports features such as code execution, result feedback, and REPL interaction.
• Applicable Scenarios: Developers can collaborate with AI assistants to complete coding tasks.

📚 Documentation

The above diagram shows the overall architecture of the Calva MCP Server, including the user, AI assistant, VS Code environment, and project structure. Through this bridge, AI assistants can more efficiently assist developers in code writing and debugging.

📄 License

• The copyright of the project documentation belongs to the author.
• If you need to quote or modify it, please indicate the source.

🤝 Sponsorship Information

If you like this project, you can support the author in the following ways:

• GitHub: [Your GitHub Link]
• Sponsor: [Sponsor Link]

Thank you for reading!