AI agents call lsp_list_servers 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 read-only operation that queries the state of language servers on the system. It retrieves and displays information (which servers exist and whether their binaries are accessible) without creating, modifying, deleting, or executing anything. The blast radius is minimal—an AI agent misusing this tool could only learn what language servers are available, which poses no direct risk.
From the tool's definition Tool name 'lsp_list_servers' and description 'List known language servers and whether their binary is on PATH' indicate a retrieval/query operation that checks status of language servers without modification.
Attacks that exploit this kind of access
List known language servers and whether their binary is on PATH. 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_list_servers: 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_list_servers 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_list_servers 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_list_servers. 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_list_servers 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 →