// SCAN REPORT

Mcp Debugger

29 tools. 16 can modify or destroy data without limits.

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

Last updated: 4 Apr 2026

16 can modify or destroy data

13 read-only

29 tools total

// TOOL MAP

Read (13) Write / Execute (14) Destructive / Financial (2)

// WHAT CAN GO WRONG

Destructive tools (debugger_remove_breakpoint, debugger_remove_watch) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

Write operations (debugger_add_watch, debugger_set_breakpoint, debugger_set_exception_breakpoint) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

Execute tools (debugger_start, debugger_start_cpu_profile, debugger_step_into) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.

One command. Full control.

Intercept sits between your agent and Mcp Debugger. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.

npx -y @policylayer/intercept scan -- npx -y @ai-capabilities-suite/mcp-debugger-server

Scans every tool. Generates a policy. Starts enforcing.

Works with Claude Code · Cursor · Claude Desktop · Windsurf · any MCP client

// RECOMMENDED RULES

Deny destructive operations

debugger_remove_breakpoint:
  rules:
    - action: deny

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

Rate limit write operations

debugger_add_watch:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

debugger_continue:
  rules:
    - rate_limit: 60/minute

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

// ALL 29 MCP DEBUGGER TOOLS

DESTRUCTIVE 2 tools

Destructive debugger_remove_breakpoint Destructive debugger_remove_watch

EXECUTE 7 tools

Execute debugger_start Execute debugger_start_cpu_profile Execute debugger_step_into Execute debugger_step_out Execute debugger_step_over Execute debugger_stop_cpu_profile Execute debugger_stop_session

WRITE 7 tools

Write debugger_add_watch Write debugger_set_breakpoint Write debugger_set_exception_breakpoint Write debugger_set_function_breakpoint Write debugger_set_hit_count_condition Write debugger_set_logpoint Write debugger_switch_stack_frame

READ 13 tools

Read debugger_continue Read debugger_detect_hang Read debugger_get_global_variables Read debugger_get_local_variables Read debugger_get_performance_metrics Read debugger_get_stack Read debugger_get_watches Read debugger_inspect Read debugger_inspect_object Read debugger_list_breakpoints Read debugger_pause Read debugger_take_heap_snapshot Read debugger_toggle_breakpoint

// FAQ

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

Yes. The Mcp Debugger server exposes 2 destructive tools including debugger_remove_breakpoint, debugger_remove_watch. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Mcp Debugger? +

The Mcp Debugger server has 7 write tools including debugger_add_watch, debugger_set_breakpoint, debugger_set_exception_breakpoint. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.

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

29 tools across 4 categories: Destructive, Execute, Read, Write. 13 are read-only. 16 can modify, create, or delete data.

How do I add Intercept to my Mcp Debugger setup? +

One line change. Instead of running the Mcp Debugger server directly, prefix it with Intercept: intercept -c io-github-digital-defiance-mcp-debugger.yaml -- npx -y @@ai-capabilities-suite/mcp-debugger-server. Download a pre-built policy from policylayer.com/policies/io-github-digital-defiance-mcp-debugger and adjust the limits to match your use case.

// RELATED SERVERS

Other MCP servers with similar tools.

Starter policies available for each. Same risk classification, same one-command setup.

policylayer/intercept

Control every MCP tool call
your agent makes.

Set budgets, approvals, and hard limits across MCP servers.

npx -y @policylayer/intercept init

Protect your agent in 30 seconds. Scans your MCP config and generates enforcement policies for every server.

Mcp Debugger

One command. Full control.

Other MCP servers with similar tools.

Control every MCP tool call your agent makes.

Control every MCP tool call
your agent makes.