// SCAN REPORT

Mcp Debugger

22 tools. 13 can modify or destroy data without limits.

13 write tools that can modify data. Rate limits recommended.

Last updated: 5 Jul 2026

13 can modify or destroy data

9 read-only

22 tools total

Community server · catalogue entry verified 05/07/2026

How to control Mcp Debugger ↓

TOOL MAP

What Mcp Debugger exposes to your agents

Read (9) Write / Execute (13) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Mcp Debugger tools

Execute · High start_debugging Debugging tools inherently execute code to inspect its behavior. Execute · High attach_to_process Attaching to a running process is an active operation that connects the debugger to an external process, enabling control over its execution (pause, step, evaluate, modify memory). Execute · High create_debug_session Creating a debug session either attaches to a live process or launches a new one. Execute · High evaluate_expression This tool executes arbitrary expressions within a live debug context.

13 of Mcp Debugger's 22 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Mcp Debugger

PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Debugger, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "close_debug_session": {
    "limits": [
      {
        "counter": "close_debug_session_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "dev_server_status": {
    "limits": [
      {
        "counter": "dev_server_status_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Mcp Debugger — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MCP DEBUGGER →

Instant setup, no code required.

FULL CATALOGUE

All 22 Mcp Debugger tools

EXECUTE 11 tools

Execute attach_to_process Attach to a running process for debugging Execute continue_execution Continue execution Execute create_debug_session Create a new debugging session. Provide host and port to attach to a running process; omit them for launch mod Execute detach_from_process Detach from the debugged process without terminating it Execute evaluate_expression Evaluate expression in the current debug context. Expressions can read and modify program state Execute pause_execution Pause a running program Execute redefine_classes Hot-swap changed Java classes into a running JVM. Scans a classes directory for .class files modified after si Execute start_debugging Start debugging a script Execute step_into Step into Execute step_out Step out Execute step_over Step over

WRITE 2 tools

Write close_debug_session Close a debugging session Write set_breakpoint Set a breakpoint. Setting breakpoints on non-executable lines (structural, declarative) may lead to unexpected

READ 9 tools

Read dev_server_status Get the current status of the mcp-debugger backend (state, PID, uptime, tool count, port). Read get_local_variables Get local variables for the current stack frame. This is a convenience tool that returns just the local variab Read get_scopes Get scopes for a stack frame Read get_source_context Get source context around a specific line in a file Read get_stack_trace Get stack trace Read get_variables Get variables (scope is variablesReference: number) Read list_debug_sessions List all active debugging sessions Read list_supported_languages List all supported debugging languages with metadata Read list_threads List all threads in the debugged process

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Mcp Debugger

How do I prevent bulk modifications through Mcp Debugger? +

The Mcp Debugger server has 2 write tools including close_debug_session, set_breakpoint. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Mcp Debugger.

How many tools does the Mcp Debugger MCP server expose? +

22 tools across 3 categories: Execute, Read, Write. 9 are read-only. 13 can modify, create, or delete data.

How do I enforce a policy on Mcp Debugger? +

Register the Mcp Debugger MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Mcp Debugger tool call.

Deterministic rules across all 22 Mcp Debugger tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP DEBUGGER →

Instant setup, no code required.

22 Mcp Debugger tools catalogued and risk-classified — across an index of 43,000+ MCP servers.