AI agents call lsp_signature_help to retrieve information from Lsp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about function signatures from a language server—purely informational. It does not execute code, modify files, delete data, or trigger external operations. It is analogous to hovering over a function in an IDE to see its signature. The blast radius of misuse is negligible: an AI agent cannot cause harm by requesting signature information.
From the tool's definition Tool description states it 'Get[s] parameter hints for a function call' and provides information about 'what arguments a function expects and their types'. The words 'Get' and 'hints' indicate a read-only query operation with no side effects.
Attacks that exploit this kind of access
Get parameter hints for a function call. Use when you need to know what arguments a function expects and their types, especially for overloaded functions. It is categorised as a Read tool in the Lsp MCP Server, which means it retrieves data without modifying state.
Register the Lsp MCP server in PolicyLayer and add a rule for lsp_signature_help: 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 Lsp. Nothing to install.
lsp_signature_help 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_signature_help 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_signature_help. 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_signature_help is provided by the Lsp MCP server (lsp-mcp-server). 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 →