AI agents call lsp_status 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 tool reports the status of language servers and toolchains, which is purely informational. It queries the local system state to determine what development tools are installed or active, with no side effects, data modification, or code execution involved. This is a classic Read operation with minimal security risk.
From the tool's definition 'Report which language servers / toolchains are available' — a query operation that retrieves configuration/availability status without modification or execution of external services.
Attacks that exploit this kind of access
Report which language servers / toolchains are available. 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_status: 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_status 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_status 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_status. 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_status 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 →