find_usages
AI agents call find_usages to retrieve information from Codebase Contextifier 9000 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
find_usages retrieves information about where code elements are referenced within the codebase. This is a passive read operation with no side effects—it queries the indexed codebase but does not create, modify, delete, or execute anything. The blast radius of misuse is minimal; an agent could retrieve more code context than intended, but cannot alter or execute code.
From the tool's definition Tool name 'find_usages' indicates a search or query operation. Sibling tools ('find_callees', 'find_callers', 'get_call_graph', 'get_class_hierarchy') are all read-only analysis functions.
Attacks that exploit this kind of access
find_usages. It is categorised as a Read tool in the Codebase Contextifier 9000 MCP Server, which means it retrieves data without modifying state.
Register the Codebase Contextifier 9000 MCP server in PolicyLayer and add a rule for find_usages: 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 Codebase Contextifier 9000. Nothing to install.
find_usages 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_usages 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_usages. 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_usages is provided by the Codebase Contextifier 9000 MCP server (jarmentor/codebase-contextifier-9000). 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 →