What is jetbrains-debugger-mcp-plugin CLAUDE.md?

Instructions for using a JetBrains IDE debugger through MCP, a standard way for software tools to communicate with an AI agent. A debugger pauses a running program so its code and values can be inspected.

Use it to discover debug configurations, start sessions, set breakpoints, resume and pause execution, inspect stack traces and variables, evaluate expressions, and step through programs.

It provides a repeatable process for finding bugs by setting breakpoints, stepping through code, examining variables, and testing expressions.

How hechtcarmel/jetbrains-debugger-mcp-plugin configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to hechtcarmel/jetbrains-debugger-mcp-plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/hechtcarmel/jetbrains-debugger-mcp-plugin/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/hechtcarmel/jetbrains-debugger-mcp-plugin

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hechtcarmel/jetbrains-debugger-mcp-plugin/claude-md/github.svg)](https://agentmods.dev/instructions/hechtcarmel/jetbrains-debugger-mcp-plugin/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/hechtcarmel/jetbrains-debugger-mcp-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/hechtcarmel/jetbrains-debugger-mcp-plugin/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hechtcarmel/jetbrains-debugger-mcp-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/hechtcarmel/jetbrains-debugger-mcp-plugin/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,946 This file is loaded in full into every session.

When invoked 4,946 The same file — it is already loaded in full.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.04946	$0.04946
Opus 5.5	$0.01978	$0.01978
Sonnet 5.5	$0.00989	$0.00989
Haiku 4.5	$0.00495	$0.00495

Measured 2d ago against content hash 130db068c132, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

jetbrains-debugger-mcp-plugin CLAUDE.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

the blocklist is JVM-specific, so `os.system`, `require('child_process')` and similar pass

CLAUDE.md · 432 lines

How it starts

The opening of the file, as written. The whole thing — 432 lines — stays where its author put it; the contents beside it link to each section on GitHub.

JetBrains Debugger MCP Plugin

This plugin exposes JetBrains IDE debugger capabilities through MCP (Model Context Protocol), enabling AI agents to programmatically debug applications.

Quick Start

IMPORTANT: When debugging, prefer using jetbrains-debugger MCP tools to interact with the IDE debugger.

Typical Debugging Workflow

Discover configurations: list_run_configurations to see available run/debug configs
Start debugging: start_debug_session with a configuration that has can_debug: true
Set breakpoints: set_breakpoint at locations of interest
Resume and wait: resume_execution then wait_for_pause with a timeout to block until a breakpoint is hit
Inspect state: wait_for_pause returns variables, stack trace, and source context automatically. Use get_debug_session_status if you need to re-inspect without waiting.
Evaluate expressions: evaluate_expression to test hypotheses
Step through code: step_over, step_into, step_out as needed
Repeat steps 5-7 until the issue is found

Tool Reference

Session Management

Tool	Description
`list_run_configurations`	List available run configurations
`execute_run_configuration`	Run a configuration (debug or run mode)
`list_debug_sessions`	List active debug sessions
`list_android_processes`	List running Android processes by device serial, PID and exact name
`attach_android_debugger`	Attach the Android debugger to a running Android app process
`start_debug_session`	Start a new debug session
`stop_debug_session`	Stop a debug session
`get_debug_session_status`	Get comprehensive session state (variables, stack, source)
`get_console_output`	Read retained console text and logpoint results while running or paused

Breakpoints

Tool	Description
`list_breakpoints`	List all breakpoints
`set_breakpoint`	Set a line breakpoint (supports conditions, log messages)
`remove_breakpoint`	Remove a breakpoint by ID

Read the full file on GitHub · 432 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago Changed · +30 lines · +479 tokens per session 130db068c132
12d ago Changed · +5 lines · +168 tokens per session fcfdfe262e40
1mo ago Changed · +17 lines · +419 tokens per session 3985f6a55956
2mo ago First seen · 380 lines · 3,880 tokens per session scan A 7b495d6ae09a

Subscribe to this mod's changes

jetbrains-debugger-mcp-plugin CLAUDE.md is an instructions file published in the GitHub repository hechtcarmel/jetbrains-debugger-mcp-plugin (117 stars, last pushed 3d ago), licensed MIT. It adds 4,946 tokens to every session, about $0.0198 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Debugging

jetbrains-debugger-mcp-plugin CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
jetbrains-debugger-mcp-plugin CLAUDE.mdhechtcarmel/jetbrains-debugger-mcp-plugin	Instructions file	117	3d ago	MIT	A	4,946	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

jetbrains-debugger-mcp-plugin: Instructions file for Claude Code