Return markdown hover contents for the identifier at a zero-based LSP position.
AI agents call lsp_hover to retrieve information from Syntax Map without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
lsp_hover provides IDE-style hover information (typically documentation, type signatures, or symbol metadata) for code analysis purposes. It reads existing data structures and symbols without modifying, deleting, or executing any code. This is a standard Read operation common in language server implementations.
From the tool's definition Tool returns markdown hover contents for an identifier at a given LSP position. This is purely a query/lookup operation with no side effects. The description uses 'Return' indicating data retrieval only.
Attacks that exploit this kind of access
Return markdown hover contents for the identifier at a zero-based LSP position. It is categorised as a Read tool in the Syntax Map MCP Server, which means it retrieves data without modifying state.
Register the Syntax Map MCP server in PolicyLayer and add a rule for lsp_hover: 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 Syntax Map. Nothing to install.
lsp_hover 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_hover 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_hover. 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_hover is provided by the Syntax Map MCP server (kht6163/syntax-map-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 →