AI agents call lookup_function to retrieve information from Lsl without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves LSL function documentation from the official Second Life wiki database. It has no side effects, does not execute code, and does not modify any data. The empty description lowers confidence slightly, but the server's stated purpose and naming pattern clearly indicate this is a read-only reference lookup tool.
From the tool's definition Tool name 'lookup_function' and server purpose indicates querying LSL reference data. Description is empty but context from sibling tools (search_functions, get_constants, list_events) all perform read-only reference lookups.
Attacks that exploit this kind of access
lookup_function. It is categorised as a Read tool in the Lsl MCP Server, which means it retrieves data without modifying state.
Register the Lsl MCP server in PolicyLayer and add a rule for lookup_function: 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 Lsl. Nothing to install.
lookup_function 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 lookup_function 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 lookup_function. 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.
lookup_function is provided by the Lsl MCP server (treeeeeeeeeeeeee/second-life-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 →