AI agents call lsp_call_hierarchy 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 queries code structure metadata (call hierarchies) without side effects. It is analogous to lsp_find_references and lsp_find_implementations, which are standard code analysis operations. The mention of 'assessing impact before modifying' reinforces that this is a preparatory read-only step. The severity is low because misuse causes no damage—at worst, an agent obtains code relationship information.
From the tool's definition Tool description states it 'Trace[s] function calls' and is 'Essential for understanding code flow' — purely informational operations. No modification, deletion, or execution of code is performed; it only analyzes and retrieves call relationships.
Attacks that exploit this kind of access
Trace function calls: who calls this function (incoming) and what it calls (outgoing). Essential for understanding code flow and assessing impact before modifying a function. 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_call_hierarchy: 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_call_hierarchy 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_call_hierarchy 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_call_hierarchy. 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_call_hierarchy 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.
lsp_call_hierarchy is one line of Lsp's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →