AI agents call find_symbol to retrieve information from Knocoph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information from an indexed SQLite knowledge graph without creating, modifying, deleting, or executing anything. It is a query/lookup operation with no side effects on the codebase or system. The severity is low because misuse would only expose code structure and content that the AI already has access to, with no destructive, financial, or operational consequences.
From the tool's definition Tool description states it 'Locate[s] a symbol by name in the code graph' and 'Returns node id, file path, line range, and optionally the source code.' The phrase 'Always call this before opening files' indicates it retrieves metadata and code content without…
Attacks that exploit this kind of access
Locate a symbol by name in the code graph. Returns node id, file path, line range, and optionally the source code. Always call this before opening files. It is categorised as a Read tool in the Knocoph MCP Server, which means it retrieves data without modifying state.
Register the Knocoph MCP server in PolicyLayer and add a rule for find_symbol: 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 Knocoph. Nothing to install.
find_symbol 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_symbol 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_symbol. 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_symbol is provided by the Knocoph MCP server (jagonzalr/knocoph). 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 →