
Node.js Debugger MCP Server
Provides Node.js debugging capabilities with process management for AI agents, allowing them to start/stop Node.js processes, set breakpoints, step through code, and evaluate expressions.
Tools
start_node_process
Start a Node.js process with debugging enabled
kill_process
Kill a managed Node.js process
list_processes
List all managed Node.js processes
attach_debugger
Attach debugger to a running Node.js process
set_breakpoint
Set a breakpoint in the debugged process. Use full file:// URLs for reliable breakpoint hits.
step_debug
Step through code execution
pause_execution
Pause execution of the debugged process
evaluate_expression
Evaluate an expression in the current debug context
README
Node.js Debugger MCP Server
An MCP server that provides Node.js debugging capabilities with process management for AI agents.
Features
- Process Management: Start/stop Node.js processes with debugging enabled
- Debugging Tools: Set breakpoints, step through code, evaluate expressions
- Inspector Integration: Connect to Node.js Inspector API
- AI Agent Friendly: Designed for long-running debugging sessions
Installation
-
Build the server:
npm install npm run build
-
For Project-Specific Use: The
.mcp.json
file is already configured in this project -
For User-Wide Use: Add to your global Claude Code configuration:
claude mcp add --scope user debugger-mcp node /absolute/path/to/debugger-mcp/build/index.js
-
For Global Use: Copy the
.mcp.json
to your projects or add to global config
Usage with Claude Code
Once configured, you'll have access to these tools in Claude Code:
Process Management
start_node_process
- Launch Node.js scripts with debuggingkill_process
- Terminate processes by PIDlist_processes
- Show all managed processes
Debugging
attach_debugger
- Connect to debug portset_breakpoint
- Set breakpoints with optional conditions- Important: Use full
file://
URLs for reliable breakpoint hits - Example:
file:///Users/you/project/script.js
- Important: Use full
step_debug
- Step through code (next/step/continue/out)pause_execution
- Manually pause a running processevaluate_expression
- Evaluate expressions in debug context
Resources
debug://session
- Current debug session statedebug://processes
- List of managed processes
Example Usage
-
Start a Node.js process:
Use the start_node_process tool with script: "example-app.js"
-
Attach debugger:
Use attach_debugger tool with the port returned from step 1
-
Set breakpoints and debug:
# Set a breakpoint using full file URL Use set_breakpoint tool with: - file: "file:///absolute/path/to/example-app.js" - line: 5 # Control execution Use step_debug tool with action: "continue"
Key Features
- Automatic Pause on Start: Uses
--inspect-brk
flag to pause at first line - Full Chrome DevTools Protocol: Real debugging, not simulation
- Reliable Breakpoints: Use
file://
URLs for consistent breakpoint hits - Process Management: Track and manage multiple debugging sessions
Testing
Test with the included example app:
node --inspect=9229 example-app.js
Then use the MCP tools to debug it!
Debug the MCP Server
npm run inspector
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.