Run a read-only/info/show style command.
AI agents call get to retrieve information from OpenSimulator MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool is designed to query and display information about OpenSimulator server state (regions, users, terrain, objects, etc.) without causing side effects. Even though it operates on a virtual world system, read-only operations pose minimal direct risk. Severity is low because the blast radius is limited to information disclosure.
From the tool's definition Tool description explicitly states 'read-only/info/show style command', which retrieves information without modifying state.
Attacks that exploit this kind of access
Run a read-only/info/show style command. It is categorised as a Read tool in the OpenSimulator MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenSimulator MCP Server MCP server in PolicyLayer and add a rule for get: 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 OpenSimulator MCP Server. Nothing to install.
get 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 get 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 get. 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.
get is provided by the OpenSimulator MCP Server MCP server (sanchorelaxo/opensim-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 →