DebugMCP (MCP Server) - Empowering AI Agents with Operational Debugging Capabilities

Let AI agents debug your code inside VS Code - set breakpoints, step through execution, inspect variables, and evaluate expressions. Works with Codex, GitHub Copilot, GitHub Copilot CLI, Cline, Cursor, Windsurf, Roo Code, and any MCP-compatible assistant. Compatible with any VS Code supported coding language.

⭐ If you find DebugMCP useful, please star the repo on GitHub! It helps others discover the project and motivates continued development.

📢 Developers Notice: This extension is maintained by ozzafar@microsoft.com and orbarila@microsoft.com. We welcome feedback and contributions to help improve this extension.

🎬 Watch DebugMCP in action — your AI assistant autonomously sets breakpoints, steps through code, and inspects variables directly in VS Code.

✨ What's New in 2.0.0

• /debug Agent Skill — DebugMCP now ships a companion Agent Skill that is auto-installed into each configured harness's personal skills directory (e.g. ~/.copilot/skills/debug/). Invoke it with /debug in supporting agents to load the systematic debugging workflow and trigger DebugMCP tools with the right context.
• Robust debugging via the VS Code Testing API — start_debugging with a testName now uses the VS Code Testing API to discover and launch the test, replacing the previous best-effort path. This works reliably across language test runners that integrate with the Testing API (pytest, Jest/Vitest, Java, .NET, Go, etc.) and produces consistent breakpoint hits inside individual test cases.

🚀 Quick Install

Install from VS Code Marketplace or use the direct link: vscode:extension/ozzafar.debugmcpextension

Table of Contents

• Overview
• Features
• Installation
• Quick Start
• Supported AI Assistants
• Supported Languages
• Configuration
• FAQ
• Troubleshooting
• How It Works
• Contributing
• License

Overview

DebugMCP is an MCP server that gives AI coding agents full control over the VS Code debugger. Instead of reading logs or guessing, your AI assistant can autonomously set breakpoints, launch debug sessions, step through code line by line, inspect variable values, and evaluate expressions — just like a human developer would. It runs 100% locally, requires zero configuration, and works out of the box with any MCP-compatible AI assistant.

Features

🔧 Tools

Tool	Description	Parameters
start_debugging	Start a debug session for a source code file	fileFullPath (required) workingDirectory (required) testName (optional) configurationName (optional)
stop_debugging	Stop the current debug session	None
step_over	Execute the next line (step over function calls)	None
step_into	Step into function calls	None
step_out	Step out of the current function	None
continue_execution	Continue until next breakpoint	None
restart_debugging	Restart the current debug session	None
add_breakpoint	Add a breakpoint at a specific line	fileFullPath (required) lineContent (required)
remove_breakpoint	Remove a breakpoint from a specific line	fileFullPath (required) line (required)
clear_all_breakpoints	Remove all breakpoints at once	None
list_breakpoints	List all active breakpoints	None
get_variables_values	Get variables and their values at current execution point	scope (optional: 'local', 'global', 'all')
evaluate_expression	Evaluate an expression in debug context	expression (required)

Note: The MCP server intentionally exposes tools only — no procedural instructions, no documentation resources. Workflow guidance (when to debug, how to structure a root-cause investigation, language-specific quirks) lives in the companion DebugMCP Agent Skill so it can be loaded into an agent's prompt context independently of the MCP capability surface.

🎯 Debugging Best Practices

DebugMCP follows systematic debugging practices for effective issue resolution:

• Start with Entry Points: Begin debugging at function entry points or main execution paths
• Follow the Execution Flow: Use step-by-step execution to understand code flow
• Root Cause Analysis: Don't stop at symptoms - find the underlying cause

🛡️ Security & Reliability

• Secure Communication: All MCP communications use secure protocols
• Local Operation: The MCP server runs 100% locally with no external communications and requires no credentials
• State Validation: Robust validation of debugging states and operations

Installation

Quick Install Options

Option 1: Direct Link (Fastest)

• Click this link: vscode:extension/ozzafar.debugmcpextension
• Or copy and paste in your browser: vscode:extension/ozzafar.debugmcpextension

Option 2: VS Code Marketplace

• Visit: https://marketplace.visualstudio.com/items?itemName=ozzafar.debugmcpextension
• Click "Install"

Option 3: Within VS Code

1. Open VSCode
2. Go to Extensions (Ctrl+Shift+X / Cmd+Shift+X)
3. Search for "DebugMCP"
4. Click Install
5. The extension automatically activates and registers as an MCP server

Verification

After installation, you should see:

• DebugMCP extension in your installed extensions
• MCP server automatically running on port 3001 (configurable)
• Debug tools available to connected AI assistants

📝 Note: No additional debugging rule instructions are needed - the extension works out of the box.

💡 Tip: Enable auto-approval for all debugmcp tools in your AI assistant to create seamless debugging workflows without constant approval interruptions.

Quick Start

1. Install the extension (see Installation)
2. Open your project in VSCode
3. Ask your AI to debug - it can now set breakpoints, start debugging, and analyze your code!

Supported AI Assistants

DebugMCP works with any MCP-compatible AI assistant. It auto-detects and offers to register itself with:

Assistant	Auto-Registration	Manual Config
GitHub Copilot	✅	See config
GitHub Copilot CLI	✅	See config
Cline	✅	See config
Cursor	✅	See config
Codex	✅	See config
Windsurf	✅	See config
Roo Code	✅	See config
Antigravity	✅	See config
Any MCP-compatible assistant	—	See manual setup

Supported Languages

DebugMCP supports debugging for the following languages with their respective VSCode extensions:

Language	Extension Required	File Extensions	Status
Python	Python	.py	✅ Fully Supported
JavaScript/TypeScript	Built-in / JS Debugger	.js, .ts, .jsx, .tsx	✅ Fully Supported
Java	Extension Pack for Java	.java	✅ Fully Supported
C/C++	C/C++	.c, .cpp, .cc	✅ Fully Supported
Go	Go	.go	✅ Fully Supported
Rust	rust-analyzer	.rs	✅ Fully Supported
PHP	PHP Debug	.php	✅ Fully Supported
Ruby	Ruby	.rb	✅ Fully Supported
C#/.NET	C#	.cs, .csproj	✅ Fully Supported

Configuration

MCP Server Configuration (Recommended)

The extension runs an MCP server automatically. It will pop up a message to auto-register the MCP server in your AI assistant.

You can also trigger the registration manually via the Command Palette:

• DebugMCP: Show Agent Selection Popup

Manual MCP Server Registration (Optional)

🔄 Auto-Migration: If you previously configured DebugMCP with SSE transport, the extension will automatically migrate your configuration to the new Streamable HTTP transport on activation.

Cline

Add to your Cline settings or cline_mcp_settings.json:

{
  "mcpServers": {
    "debugmcp": {
      "type": "streamableHttp",
      "url": "http://localhost:3001/mcp",
      "description": "DebugMCP - AI-powered debugging assistant"
    }
  }
}

GitHub Copilot

Add to your VS Code settings (settings.json):

{
  "mcp": {
    "servers": {
      "debugmcp": {
        "type": "http",
        "url": "http://localhost:3001/mcp",
        "description": "DebugMCP - Multi-language debugging support"
      }
    }
  }
}

GitHub Copilot CLI

Add to ~/.copilot/mcp-config.json (${COPILOT_HOME}/mcp-config.json if COPILOT_HOME is set):

{
  "mcpServers": {
    "debugmcp": {
      "type": "http",
      "url": "http://localhost:3001/mcp",
      "tools": ["*"]
    }
  }
}

Cursor

Add to Cursor's MCP settings:

{
  "mcpServers": {
    "debugmcp": {
      "type": "streamableHttp",
      "url": "http://localhost:3001/mcp",
      "description": "DebugMCP - Debugging tools for AI assistants"
    }
  }
}

Codex

Register DebugMCP with Codex:

codex mcp add debugmcp --url http://localhost:3001/mcp

Or add the equivalent configuration to ~/.codex/config.toml (${CODEX_HOME}/config.toml if CODEX_HOME is set):

[mcp_servers.debugmcp]
url = "http://localhost:3001/mcp"

Windsurf

Add to Windsurf's MCP settings (~/.windsurf/mcp_settings.json or workspace .windsurf/mcp_settings.json):

{
  "mcpServers": {
    "debugmcp": {
      "type": "streamableHttp",
      "url": "http://localhost:3001/mcp",
      "description": "DebugMCP - Debugging tools for AI assistants"
    }
  }
}

Roo Code

Add to Roo Code's MCP settings:

{
  "mcpServers": {
    "debugmcp": {
      "type": "streamableHttp",
      "url": "http://localhost:3001/mcp",
      "description": "DebugMCP - Debugging tools for AI assistants"
    }
  }
}

Antigravity

Add to Antigravity's MCP settings:

{
  "mcpServers": {
    "debugmcp": {
      "type": "streamableHttp",
      "url": "http://localhost:3001/mcp",
      "description": "DebugMCP - Debugging tools for AI assistants"
    }
  }
}

Extension Settings

Configure DebugMCP behavior in VSCode settings:

{
  "debugmcp.serverPort": 3001,
  "debugmcp.timeoutInSeconds": 180,
  "debugmcp.bindHost": ["127.0.0.1", "::1"]
}

Setting	Default	Description
debugmcp.serverPort	3001	Port number for the MCP server
debugmcp.timeoutInSeconds	180	Timeout for debugging operations
debugmcp.bindHost	["127.0.0.1", "::1"]	Network interface(s) the HTTP server binds to. Accepts a string or array of strings. See Security model before changing.

Security model

DebugMCP exposes powerful debugger primitives (evaluate_expression, start_debugging, …) over an unauthenticated local HTTP endpoint. To keep that surface safe, the server enforces two controls:

1. Loopback-only bind. The HTTP server binds to the IPv4 and IPv6 loopback addresses (127.0.0.1 and ::1) by default, so other hosts on your network cannot reach http://<your-ip>:3001/mcp. Binding both families ensures clients that resolve localhost to either family connect successfully. The debugmcp.bindHost setting (string or array of strings) lets you opt into a different interface (for example, when forwarding the port into a remote container), but doing so exposes the unauthenticated debugger to anything that can route to that address — do not point it at 0.0.0.0 or a LAN address on an untrusted network.
2. Host / Origin header validation. Every request must carry a Host header naming a loopback address (localhost, 127.0.0.1, or [::1]); any port suffix in the Host must also match the server's listening port. Requests with any other Host — including those that arrive via DNS rebinding from a malicious webpage — are rejected with HTTP 403. The same loopback check is applied to the Origin header when present.

FAQ

Which AI assistants are supported?

DebugMCP works with any MCP-compatible AI assistant, including GitHub Copilot, GitHub Copilot CLI, Cline, Cursor, Codex, Windsurf, Roo Code, Antigravity, and others. If your assistant supports the Model Context Protocol, it can use DebugMCP.

Does it work with VS Code Remote SSH / Codespaces / WSL?

Yes. DebugMCP runs as a VS Code extension with extensionKind: workspace, so it activates in the remote environment where your code lives. The MCP server runs on localhost within that remote context.

Do I need to configure launch.json?

No. DebugMCP automatically generates appropriate debug configurations based on the file's language/extension. If you have a launch.json, it will automatically pick the most relevant configuration.

Is my code sent to any external service?

No. DebugMCP runs 100% locally. The MCP server runs on localhost, and no code, variables, or debug data is sent to any external service. The AI assistant communicates with the MCP server entirely within your local machine.

What if port 3001 is already in use?

Change the port in VS Code settings: "debugmcp.serverPort": 3002 (or any available port). Then update your AI assistant's MCP configuration to use the new port.

Can I debug unit tests?

Yes. Pass the testName parameter to start_debugging to debug a specific test method. DebugMCP will configure the debug session to run and pause at breakpoints within that test.

Why is my AI assistant not using the debug tools?

Make sure DebugMCP is registered in your AI assistant's MCP settings. The extension should auto-detect and offer to register itself. If not, see the Manual MCP Server Registration section. Also enable auto-approval for DebugMCP tools for a smoother workflow.

Does it support ASP.NET / .csproj projects?

Yes. DebugMCP supports .cs files and .csproj project files for C#/.NET debugging, including ASP.NET applications.

Troubleshooting

Common Issues

MCP Server Not Starting

• Symptom: AI assistant can't connect to DebugMCP
• Solution:
  • Check if port 3001 is available
  • Restart VSCode
  • Verify extension is installed and activated

Debug Session Not Stopping at Breakpoints

• Symptom: Breakpoints are set but execution doesn't pause
• Solution:
  • Ensure the correct file is being debugged
  • Check that the breakpoint line content matches exactly
  • Verify the relevant language debugger extension is installed

Configuration Not Auto-Detected

• Symptom: Extension doesn't prompt to register with your AI assistant
• Solution:
  • Run DebugMCP: Show Agent Selection Popup from the Command Palette (Ctrl+Shift+P / Cmd+Shift+P)
  • Manually add the configuration (see Manual MCP Server Registration)

How It Works

Architecture

AI Agent (Copilot/Cline/Cursor/Codex) → MCP/Streamable HTTP → DebugMCPServer → DebuggingHandler → VS Code Debug API

Launch Configuration Integration

The extension handles debug configurations intelligently:

• Existing launch.json: If a .vscode/launch.json file exists, it will:

  • Search for a relevant configuration
  • Honor configurationName when explicitly provided by the agent
  • Support JSONC (JSON with comments and trailing commas)

• Default Configuration: If configurationName is omitted, or if no matching named configuration is found, it creates an appropriate default configuration for each language based on file extension detection

Requirements

• VSCode with appropriate language extensions installed:
  • Python: Python extension for .py files
  • JavaScript/TypeScript: Built-in Node.js debugger or JavaScript Debugger extension
  • Java: Extension Pack for Java
  • C#/.NET: C# extension
  • C/C++: C/C++ extension
  • Go: Go extension
  • Rust: rust-analyzer extension
  • PHP: PHP Debug extension
  • Ruby: Ruby extension with debug support
• MCP-compatible AI assistant (Copilot, Cline, Cursor, Codex, Windsurf, Roo Code, etc.)

Development

To build the extension:

npm install
npm run compile

To run linting:

npm run lint

To run tests:

npm test

Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

Security

Security vulnerabilities should be reported following the guidance at https://aka.ms/SECURITY.md. Please do not report security vulnerabilities through public GitHub issues.

Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.

⭐ Support DebugMCP

If DebugMCP has helped you debug faster, please consider giving it a star on GitHub! Stars help the project gain visibility and attract contributors.

⭐ Star DebugMCP on GitHub

Star History

License

MIT License - See LICENSE for details

This extension was created by Oz Zafar, Ori Bar-Ilan and Karin Brisker.