Find all usages of a function, variable, class, or identifier
AI agents call find_usage to retrieve information from Tree-Sitter MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs semantic code search and tracing, which are non-mutating read operations. It queries the codebase to locate where identifiers are used but does not create, modify, delete, execute, or move resources. The blast radius of misuse is minimal — at worst, it could expose information about code structure to an unauthorized user, but cannot cause operational damage.
From the tool's definition Tool description states 'Find all usages' — a query operation that retrieves information about code references without modifying or executing code.
Documented attack patterns abuse exactly the kind of access find_usage gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tree-Sitter MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for find_usage:
{
"version": "1",
"default": "deny",
"tools": {
"find_usage": {}
}
}find_usage 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.
Find all usages of a function, variable, class, or identifier. It is categorised as a Read tool in the Tree-Sitter MCP MCP Server, which means it retrieves data without modifying state.
Register the Tree-Sitter MCP server in PolicyLayer and add a rule for find_usage: 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 Tree-Sitter MCP. Nothing to install.
find_usage 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_usage 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_usage. 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_usage is provided by the Tree-Sitter MCP server (nendotools/tree-sitter-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Tree-Sitter MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Tree-Sitter MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.