// SCAN REPORT

Debugger MCP Server

41 tools. 15 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 1 Jul 2026

15 can modify or destroy data

26 read-only

41 tools total

Community server · catalogue entry verified 01/07/2026

How to control Debugger MCP Server ↓

TOOL MAP

What Debugger MCP Server exposes to your agents

Read (26) Write / Execute (13) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Debugger MCP Server tools

Destructive · Medium clear-browser-cache Clearing the browser cache permanently removes cached resources. Destructive · High clear-browser-cookies Clearing browser cookies permanently removes stored session and authentication data. Execute · Medium force-garbage-collection Forcing garbage collection is an external runtime operation that triggers the V8 (or equivalent) garbage collector, affecting application memory state. Execute · Medium start-cpu-profiling This tool triggers code execution and monitoring operations on a running application.

15 of Debugger MCP Server's 41 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Debugger MCP Server

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

Deny destructive operations

{
  "clear-browser-cache": {
    "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

{
  "manage-watch-expressions": {
    "limits": [
      {
        "counter": "manage-watch-expressions_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze-code-quality-ai": {
    "limits": [
      {
        "counter": "analyze-code-quality-ai_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 Debugger MCP Server — 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 DEBUGGER →

Instant setup, no code required.

FULL CATALOGUE

All 41 Debugger MCP Server tools

DESTRUCTIVE 2 tools

Destructive clear-browser-cache Clear the browser cache to test performance without cached resources Destructive clear-browser-cookies Clear browser cookies for testing authentication and session handling

EXECUTE 10 tools

Execute evaluate-expression Evaluate JavaScript expressions in the context of a call frame Execute force-garbage-collection Force garbage collection to free memory and analyze memory leaks Execute manage-breakpoints Set, remove, list, and manage breakpoints for debugging Execute modify-variable Modify variable values in a specific scope Execute set-network-throttling Configure network throttling to simulate different connection speeds Execute start-cpu-profiling Start CPU profiling to analyze performance bottlenecks and generate flame graphs Execute start-heap-sampling Start heap sampling for memory profiling and leak detection Execute start-render-tracking Start tracking render performance for a specific component Execute stop-cpu-profiling Stop CPU profiling and get the profile data with flame graph Execute take-heap-snapshot Take a detailed heap snapshot using Chrome DevTools for memory analysis

WRITE 3 tools

Write manage-watch-expressions Manage persistent watch expressions Write resolve-performance-alert Mark a performance alert as resolved Write update-config Update debugger configuration rules and settings

READ 26 tools

Read analyze-code-quality-ai Analyze code quality using AI for advanced code smell detection, refactoring opportunities, and technical debt Read analyze-complexity Analyze complexity metrics for a specific file Read analyze-errors-ai Analyze errors using AI for categorization, pattern detection, and intelligent insights Read analyze-network-performance Analyze network request patterns, identify slow requests, and get optimization recommendations Read analyze-react-component Analyze React components for state, props, hooks, and performance issues Read analyze-render-performance Analyze React component render performance, identify slow renders, and get optimization recommendations Read detect-react-issues Detect common React anti-patterns, props drilling, unnecessary re-renders, and optimization opportunities Read get-debug-session Get current debugging session information Read get-detailed-render-metrics Get comprehensive render metrics including component-level performance data and trends Read get-errors Get current errors and exceptions Read get-memory-snapshots Get memory usage snapshots for leak detection and analysis Read get-network-metrics Get network request performance metrics and timing analysis Read get-performance Get current performance metrics and insights Read get-performance-alerts Get performance alerts and warnings for CPU, memory, network, and render issues Read get-performance-dashboard Get a comprehensive performance dashboard with all key metrics, alerts, and recommendations Read get-performance-insights Get AI-powered performance analysis including bottleneck identification, optimization suggestions, and regress Read get-performance-optimization-recommendations Get comprehensive performance optimization recommendations with prioritized actions, quick wins, and long-term Read get-react-performance Get React-specific performance metrics including render counts, component optimization opportunities Read get-render-metrics Get React component render performance metrics and optimization insights Read get-scope-chain Get the complete scope chain for a call frame Read get-violations Get current code quality rule violations Read inspect-variables Inspect variables in a specific scope of a call frame Read monitor-react-hooks Monitor React hooks for compliance with rules of hooks and performance issues Read stop-heap-sampling Stop heap sampling and get the memory profile Read suggest-optimizations Get AI-powered optimization suggestions across performance, code quality, and architecture Read track-component-render Complete render tracking for a component and record performance metrics

EXPLORE

Related servers

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

FAQ

Questions about Debugger MCP Server

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

Yes. The Debugger MCP Server server exposes 2 destructive tools including clear-browser-cache, clear-browser-cookies. 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 Debugger MCP Server? +

The Debugger MCP Server server has 3 write tools including manage-watch-expressions, resolve-performance-alert, update-config. 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 Debugger MCP Server.

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

41 tools across 4 categories: Destructive, Execute, Read, Write. 26 are read-only. 15 can modify, create, or delete data.

How do I enforce a policy on Debugger MCP Server? +

Register the Debugger MCP Server 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 Debugger MCP Server tool call.

Deterministic rules across all 41 Debugger MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DEBUGGER →

Instant setup, no code required.

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