Check if a function/class name already exists elsewhere in the codebase before creating it. Prevents duplicating existing logic. Call with just a
AI agents call check_duplication 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.
The tool retrieves information about existing names in the codebase to prevent duplication. It performs a lookup/search with no side effects, making it a Read operation. The severity is low because misuse would only return false information about existing code, not cause damage. High confidence because the description explicitly describes a search/query function.
From the tool's definition check_duplication: Check if a function/class name already exists elsewhere in the codebase. This queries the dependency graph to detect naming conflicts—a read-only search operation.
Documented attack patterns abuse exactly the kind of access check_duplication 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 check_duplication:
{
"version": "1",
"default": "deny",
"tools": {
"check_duplication": {}
}
}check_duplication 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.
Check if a function/class name already exists elsewhere in the codebase before creating it. Prevents duplicating existing logic. Call with just a. 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 check_duplication: 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.
check_duplication 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 check_duplication 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 check_duplication. 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.
check_duplication 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.