Get hover information (documentation, type signature) at a position
AI agents call getHover to retrieve information from TypeScript LSP MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays type information and documentation at a specific code position, similar to IDE hover tooltips. It performs no writes, deletions, code execution, or side effects. The data returned is read-only metadata that already exists in the TypeScript compiler, making this a straightforward Read operation with minimal risk.
From the tool's definition Tool name 'getHover' and description 'Get hover information (documentation, type signature) at a position' indicate a pure query operation. Returns documentation and type metadata without modifying state.
Attacks that exploit this kind of access
Get hover information (documentation, type signature) at a position. It is categorised as a Read tool in the TypeScript LSP MCP MCP Server, which means it retrieves data without modifying state.
Register the TypeScript LSP MCP server in PolicyLayer and add a rule for getHover: 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 TypeScript LSP MCP. Nothing to install.
getHover 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 getHover 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 getHover. 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.
getHover is provided by the TypeScript LSP MCP server (jaenster/ts-lsp-mcp). 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 →