AI agents call lsp_find_references 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 tool that performs static code analysis to find symbol references. It retrieves information about code structure without side effects, side-effects, or destructive operations. The tool is safe for an AI agent to use as it only reads and reports existing code references.
From the tool's definition Tool name 'lsp_find_references' and description 'Find references to the symbol at a 1-indexed line/character (TypeScript/JavaScript)' indicates a read-only query operation that locates where a symbol is referenced in code without modifying, executing, or…
Attacks that exploit this kind of access
Find references to 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_find_references: 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_find_references 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_find_references 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_find_references. 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_find_references 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 →