dap_locals

THE RISK

Low Risk

Why dap_locals needs a policy

This tool only reads and returns local variable values from a debug stack frame. It has no side effects, does not modify state, and cannot execute code or alter data. It is a pure read/inspection operation within a debugger context.

From the tool's definition Return locals from the top (or last stopped) stack frame

Documented attack patterns abuse exactly the kind of access dap_locals gives an agent:

POLICY

How to control dap_locals

PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Debugpy, and nothing reaches the server without passing your rules. This is the rule we recommend for dap_locals:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "dap_locals": {}
  }
}

dap_locals is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Mcp Debugpy — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Mcp Debugpy tools

Execute dap_continue Continue execution on the specified (or last stopped) thread. Execute dap_launch dap_launch Execute dap_shutdown Terminate the current DAP adapter session. Execute dap_step_in Step into the next function call on the active thread. Execute dap_step_out Step out of the current function on the active thread. Execute dap_step_over Step over the next line on the active thread. Execute dap_wait_for_event Wait for a specific DAP event (e.g., 'stopped'). Execute run_tests_focus Run a focused subset: pytest -k <keyword> with JSON report.

All 16 Mcp Debugpy tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about dap_locals

What does the dap_locals tool do? +

Return locals from the top (or last stopped) stack frame. It is categorised as a Read tool in the Mcp Debugpy MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on dap_locals? +

Register the Mcp Debugpy MCP server in PolicyLayer and add a rule for dap_locals: 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 Mcp Debugpy. Nothing to install.

What risk level is dap_locals? +

dap_locals is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit dap_locals? +

Yes. Add a rate_limit block to the dap_locals 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 dap_locals completely? +

Set action: deny in the PolicyLayer policy for dap_locals. 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 dap_locals? +

dap_locals is provided by the Mcp Debugpy MCP server (markomanninen/mcp-debugpy). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mcp Debugpy tool call.

Start from Mcp Debugpy, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →