Locate the definition site of a named symbol (function, class,
AI agents call find_definition to retrieve information from Code Context without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about symbol definitions in a codebase (location, context) with no side effects. It is a query/search operation that does not execute code, modify files, or delete data. The low severity reflects minimal blast radius if misused—an agent could only discover symbol locations, not alter or execute anything.
From the tool's definition Tool name 'find_definition' and description 'Locate the definition site of a named symbol' indicate retrieval of symbol location information without modification or execution.
Attacks that exploit this kind of access
Locate the definition site of a named symbol (function, class,. It is categorised as a Read tool in the Code Context MCP Server, which means it retrieves data without modifying state.
Register the Code Context MCP server in PolicyLayer and add a rule for find_definition: 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 Code Context. Nothing to install.
find_definition 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_definition 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_definition. 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_definition is provided by the Code Context MCP server (nachogeinfor-ops/code-context). 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 →