// SCAN REPORT

Polybugger

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

1 destructive tool with no built-in limits. Policy required.

Last updated: 29 Jun 2026

13 can modify or destroy data

15 read-only

28 tools total

Community server · catalogue entry verified 29/06/2026

How to control Polybugger ↓

TOOL MAP

What Polybugger exposes to your agents

Read (15) Write / Execute (12) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Polybugger tools

Destructive · Medium debug_clear_breakpoints Clearing breakpoints removes debugging configuration that may have been carefully set up. Execute · High debug_container_launch Container launch operations execute arbitrary code within a containerized environment and trigger external system operations whose effects depend on arguments (which container image, what command, environment variables, Execute · High debug_launch debug_launch starts execution of programs under debugger control. Execute · High debug_attach Based on the tool name and server context (a multi-language debugger), 'debug_attach' most likely attaches a debugger to a running process, which is an Execute-level operation — it interacts with and can control external

13 of Polybugger's 28 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Polybugger

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

Deny destructive operations

{
  "debug_clear_breakpoints": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "debug_set_breakpoints": {
    "limits": [
      {
        "counter": "debug_set_breakpoints_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "debug_container_list_processes": {
    "limits": [
      {
        "counter": "debug_container_list_processes_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 Polybugger — 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 POLYBUGGER →

Instant setup, no code required.

FULL CATALOGUE

All 28 Polybugger tools

DESTRUCTIVE 1 tools

Destructive debug_clear_breakpoints Clear breakpoints from file or all files.

EXECUTE 10 tools

Execute debug_attach debug_attach Execute debug_container_attach debug_container_attach Execute debug_container_launch debug_container_launch Execute debug_continue Continue until next breakpoint or end. Execute debug_create_session debug_create_session Execute debug_evaluate Evaluate a Python expression. Execute debug_evaluate_watches Evaluate all watch expressions and return results. Execute debug_launch debug_launch Execute debug_pause Pause a running program. Execute debug_step Step execution: over (next line), into (enter function), out (exit function).

WRITE 2 tools

Write debug_set_breakpoints debug_set_breakpoints Write debug_terminate_session Terminate session and clean up.

READ 15 tools

Read debug_container_list_processes debug_container_list_processes Read debug_get_breakpoints Get all breakpoints organized by file, including conditions, hit counts, and log messages. Read debug_get_call_chain debug_get_call_chain Read debug_get_output Get program stdout/stderr output. Read debug_get_scopes Get scopes (locals, globals) for a frame. Read debug_get_session Get session state, stop reason, and location. Read debug_get_stacktrace Get call stack frames. Read debug_get_variables Get variables from a scope or compound variable. Read debug_inspect_variable debug_inspect_variable Read debug_list_languages List supported programming languages for debugging. Read debug_list_recoverable List recoverable sessions from previous server run. Read debug_list_sessions List all active debug sessions. Read debug_poll_events Poll for events (stopped, continued, terminated). Use after launch/step. Read debug_recover_session Recover session (restores breakpoints/watches, requires re-launch). Read debug_watch Manage watch expressions: add, remove, or list.

EXPLORE

Related servers

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

FAQ

Questions about Polybugger

Can an AI agent delete data through the Polybugger MCP server? +

Yes. The Polybugger server exposes 1 destructive tools including debug_clear_breakpoints. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Polybugger? +

The Polybugger server has 2 write tools including debug_set_breakpoints, debug_terminate_session. 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 Polybugger.

How many tools does the Polybugger MCP server expose? +

28 tools across 4 categories: Destructive, Execute, Read, Write. 15 are read-only. 13 can modify, create, or delete data.

How do I enforce a policy on Polybugger? +

Register the Polybugger 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 Polybugger tool call.

Deterministic rules across all 28 Polybugger tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON POLYBUGGER →

Instant setup, no code required.

28 Polybugger tools catalogued and risk-classified — across an index of 43,000+ MCP servers.