Medium Risk

debug_state

Query the current debug session. Returns {state, breakpoints} by default. Set include_stack=true to also fetch the stack of the stopped thread; include_vars=true to also fetch frame[0] locals; include_threads=true to enumerate all threads.

Part of the Mobai server.

debug_state can modify Mobai data, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE MOBAI →

Free to start. No card required.

AI agents use debug_state to create or modify resources in Mobai. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call debug_state repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Mobai.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "debug_state": {
      "limits": [
        {
          "counter": "debug_state_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full Mobai policy for all 20 tools.

Get this rule live on your own Mobai server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY MOBAI →

View all 20 tools →

These attack patterns abuse exactly the kind of access debug_state gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so debug_state only ever does what you allow.

SECURE MOBAI →

Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the debug_state tool do? +

Query the current debug session. Returns {state, breakpoints} by default. Set include_stack=true to also fetch the stack of the stopped thread; include_vars=true to also fetch frame[0] locals; include_threads=true to enumerate all threads.. It is categorised as a Write tool in the Mobai MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on debug_state? +

Register the Mobai MCP server in PolicyLayer and add a rule for debug_state: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mobai. Nothing to install.

What risk level is debug_state? +

debug_state is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit debug_state? +

Yes. Add a rate_limit block to the debug_state rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block debug_state completely? +

Set action: deny in the PolicyLayer policy for debug_state. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides debug_state? +

debug_state is provided by the Mobai MCP server (MobAI-App/mobai-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mobai tool call.

Deterministic rules across all 20 Mobai tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.