Find symbols that are defined but never referenced elsewhere in the repo.
AI agents call find_dead_code to retrieve information from Codetree without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though find_dead_code only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Documented attack patterns abuse exactly the kind of access find_dead_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Codetree, and nothing reaches the server without passing your rules. This is the rule we recommend for find_dead_code:
{
"version": "1",
"default": "deny",
"tools": {
"find_dead_code": {}
}
}find_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.
Find symbols that are defined but never referenced elsewhere in the repo. It is categorised as a Read tool in the Codetree MCP Server, which means it retrieves data without modifying state.
Register the Codetree MCP server in PolicyLayer and add a rule for find_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 Codetree. Nothing to install.
find_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 find_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 find_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.
find_dead_code is provided by the Codetree MCP server (thinkyminer/codetree). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 23 Codetree tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
23 Codetree tools catalogued and risk-classified — across an index of 42,500+ MCP servers.