Evaluate an expression in the current debugging context.
AI agents invoke evaluate to trigger actions in Dap. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Expression evaluation in a debugger is effectively arbitrary code execution within the debugged process. An AI agent could misuse this to run destructive operations, exfiltrate data, or alter program behavior. The blast radius is high because the scope of what 'expressions' can do is broad and context-dependent.
From the tool's definition 'Evaluate an expression in the current debugging context' — evaluating arbitrary expressions in a live debugger context can execute code, modify program state, call functions, or read/write memory.
Documented attack patterns abuse exactly the kind of access evaluate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Dap, and nothing reaches the server without passing your rules. This is the rule we recommend for evaluate:
{
"version": "1",
"default": "deny",
"tools": {
"evaluate": {
"limits": [
{
"counter": "evaluate_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}evaluate stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Evaluate an expression in the current debugging context. It is categorised as a Execute tool in the Dap MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Dap MCP server in PolicyLayer and add a rule for evaluate: 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 Dap. Nothing to install.
evaluate is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the evaluate 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.
Set action: deny in the PolicyLayer policy for evaluate. 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.
evaluate is provided by the Dap MCP server (kashuncheng/dap_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Dap, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
14 Dap tools catalogued and risk-classified — across an index of 43,000+ MCP servers.