AI agents call get_dead_code to retrieve information from Trace without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Dead code detection is a static analysis capability that retrieves information about unused code paths. The 'get' verb and 'detection' phrasing confirm this is a read operation with no side effects—it does not execute code, modify sources, delete anything, or trigger external operations. The analysis scope is limited to identifying unreachable or unused code patterns, making it low-severity even in misuse scenarios.
From the tool's definition Tool name 'get_dead_code' and description 'Dead code detection' indicate a read-only analysis operation that queries/identifies unused code without modifying it.
Documented attack patterns abuse exactly the kind of access get_dead_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Trace, and nothing reaches the server without passing your rules. This is the rule we recommend for get_dead_code:
{
"version": "1",
"default": "deny",
"tools": {
"get_dead_code": {}
}
}get_dead_code is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Dead code detection. Two modes: (1). It is categorised as a Read tool in the Trace MCP Server, which means it retrieves data without modifying state.
Register the Trace MCP server in PolicyLayer and add a rule for get_dead_code: 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 Trace. Nothing to install.
get_dead_code is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_dead_code 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 get_dead_code. 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.
get_dead_code is provided by the Trace MCP server (nikolai-vysotskyi/trace-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 178 Trace tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
178 Trace tools catalogued and risk-classified — across an index of 42,500+ MCP servers.