AI agents use lsp_rename_symbol to create or update resources in LocalAnt — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your LocalAnt environment.
This tool performs a language-aware refactoring operation that updates symbol references across a project. While the changes are reversible (can be undone via version control), it materially modifies source code in multiple locations, making it Write rather than Read or Execute. The 'Risk 2' annotation suggests moderate concern. It is not Destructive (changes are reversible) or Financial.
From the tool's definition Tool description states 'Rename the symbol at a 1-indexed line/character across the project' — this modifies code across multiple files in a codebase, which is a reversible but non-trivial code change operation.
Attacks that exploit this kind of access
Rename the symbol at a 1-indexed line/character across the project (TypeScript/JavaScript). Risk 2. It is categorised as a Write tool in the LocalAnt MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the LocalAnt MCP server in PolicyLayer and add a rule for lsp_rename_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 LocalAnt. Nothing to install.
lsp_rename_symbol is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the lsp_rename_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 lsp_rename_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.
lsp_rename_symbol 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 →