Find potentially unused imports in modules
AI agents call find_unused_imports to retrieve information from FDEP MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and reports information about import statements in a codebase. It performs analysis and returns results with no side effects. Even if an AI misuses it by acting on false positives, the worst outcome is unnecessary code refactoring—a reversible action outside the scope of the tool itself.
From the tool's definition The tool description states it will "Find potentially unused imports in modules" — a query operation that analyzes code without modifying, creating, deleting, executing external commands, or committing financial transactions.
Attacks that exploit this kind of access
Find potentially unused imports in modules. It is categorised as a Read tool in the FDEP MCP Server MCP Server, which means it retrieves data without modifying state.
Register the FDEP MCP Server MCP server in PolicyLayer and add a rule for find_unused_imports: 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 FDEP MCP Server. Nothing to install.
find_unused_imports 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_unused_imports 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_unused_imports. 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_unused_imports is provided by the FDEP MCP Server MCP server (juspay/fdep-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →