AI agents call check_code 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.
While the description is empty, the tool's name 'check_code' combined with the server's stated purpose of providing reference data suggests a static analysis or validation function. There is no indication that this tool executes code, modifies data, or performs destructive operations. It appears to be a read-only reference lookup or validation tool, consistent with the other tools on this server.
From the tool's definition Tool name is 'check_code' and it is part of an LSL reference data server that provides 'accurate LSL reference data to AI coding assistants.' The sibling tools are all Read operations (get_constants, get_pitfalls, list_events, lookup_function,…
Attacks that exploit this kind of access
check_code. 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 check_code: 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.
check_code 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 check_code 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 check_code. 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.
check_code 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 →