Jeesty MCP

MCP Server for AI Assistants

An npm package that provides an MCP (Model Context Protocol) server, giving AI assistants like GitHub Copilot and Claude access to workspace tools.

Quick Start

npx jeesty-mcp init

This creates:

• .jeestymcp/config.json — tool, prompt, and resource definitions
• .jeestymcp/instructions.md — AI instructions template for your project
• Adds jeesty-mcp to your VS Code MCP config

Reload VS Code to start using the MCP server.

Configuration Location

The init command can add jeesty-mcp to two different places:

# User-level config (default) - applies to ALL your projects
npx jeesty-mcp init

# Workspace-level config - only for this project
npx jeesty-mcp init --workspace

| Config Level | Location | Scope | |--------------|----------|-------| | User | ~/.vscode/mcp.json | All VS Code workspaces | | Workspace | .vscode/mcp.json | Just this project |

Precedence: Workspace config always overrides user config. This is useful if you want a project to use a different MCP server setup (e.g., for development).

Project Configuration

Your project's .jeestymcp/ folder contains:

| File | Purpose | |------|---------| | config.json | Define custom tools, prompts, and resources | | instructions.md | AI instructions template (uses mustache variables) |

config.json Example

{
    "tools": {
        "deploy": {
            "usage": "Deploy the application to production",
            "cmd": "npm run deploy",
            "params": {
                "environment": {
                    "type": "string",
                    "description": "Target environment (staging/production)",
                    "required": true
                }
            }
        },
        "webget": {
            "usage": "Fetch content from a URL",
            "module": "scripts/webget.js",
            "params": {
                "url": { "type": "string", "description": "The URL to fetch", "required": true }
            }
        }
    },
    "prompts": {
        "explain-code": {
            "description": "Explain code in plain English",
            "template": "Please explain the following code:\n\n{{code}}"
        }
    },
    "resources": {
        "myapp://status": {
            "description": "Get app status",
            "url": "http://localhost:3000/status",
            "mimeType": "application/json"
        }
    }
}

Built-in Tools

| Tool | Description | |------|-------------| | pingJeestyMCP | Verify the MCP server is running |

Custom Tools

Tools can execute in two modes:

Command mode (cmd): Spawns a shell and runs the command

{
    "usage": "Run tests",
    "cmd": "npm test",
    "params": { ... }
}

Module mode (module): Imports a JS/TS module and calls its run() function

{
    "usage": "Fetch a URL",
    "module": "scripts/webget.js",
    "params": { ... }
}

Module mode is faster (no shell overhead) and can return structured data. The module must export:

export async function run(params: Record<string, unknown>): Promise<string | object>

Tool Parameters

Parameters support these options:

• type: "string", "number", "boolean"
• description: Help text shown to the AI
• required: Whether the parameter is required
• addToCmdWithoutKey: If true, value is passed as positional arg instead of --key=value

CLI Commands

npx jeesty-mcp init              # Add to user MCP config + create .jeestymcp/
npx jeesty-mcp init --workspace  # Add to workspace .vscode/mcp.json instead
npx jeesty-mcp remove            # Remove from user MCP config
npx jeesty-mcp --help            # Show help

How It Works

1. VS Code starts the jeesty-mcp server (via the MCP config)
2. The server searches upward from your workspace for .jeestymcp/config.json
3. AI assistants can call the provided tools to interact with your workspace
4. Custom tools execute shell commands or in-process modules and return output

Development

If you're developing jeesty-mcp itself:

Auto-Restart with Nodemon

Configure your workspace .vscode/mcp.json to use the local build with auto-restart:

{
    "servers": {
        "jeesty-mcp": {
            "type": "stdio",
            "command": "npx",
            "args": ["nodemon", "--watch", "out", "--ext", "js", "--exec", "node", "${workspaceFolder}/out/mcp-server/index.js"],
            "env": {
                "JEESTY_WORKSPACE_PATH": "${workspaceFolder}"
            }
        }
    }
}

This workspace config overrides the user-level config, so your dev environment uses the local build while other projects use the published npm package.

Dev Config Files

The repo uses legacy config file names for development (not published to npm):

• jm-config.json — dev configuration
• jm-instructions.md — dev instructions template

The MCP server checks for these as a fallback after .jeestymcp/config.json.

License

MIT