AI agents call lsp_go_to_definition to retrieve information from LocalAnt without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Language Server Protocol (LSP) query that navigates to and returns information about symbol definitions in TypeScript/JavaScript code. It reads code metadata and returns location information—a pure read operation with no side effects, no code execution, and no data modification. The blast radius of misuse is minimal; an attacker could only learn about code structure.
From the tool's definition Tool name 'lsp_go_to_definition' and description 'Find the definition of the symbol' indicate a query/lookup operation that retrieves metadata about code structure without modifying or executing anything.
Attacks that exploit this kind of access
Find the definition of the symbol at a 1-indexed line/character (TypeScript/JavaScript). It is categorised as a Read tool in the LocalAnt MCP Server, which means it retrieves data without modifying state.
Register the LocalAnt MCP server in PolicyLayer and add a rule for lsp_go_to_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 LocalAnt. Nothing to install.
lsp_go_to_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 lsp_go_to_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 lsp_go_to_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.
lsp_go_to_definition is provided by the LocalAnt MCP server (yuga-hashimoto/localant). 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 →