AI agents call socheli_fleet_status to retrieve information from Socheli without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the status of render devices in a fleet, returning read-only information about device availability and state. It has no side effects, performs no mutations, and poses minimal risk even if misused by an agent. The only potential concern is information disclosure about infrastructure, which is low severity.
From the tool's definition 'Show connected render devices and how many are online/idle/busy' — a status reporting operation that retrieves device state without modifying any data or triggering external actions.
Attacks that exploit this kind of access
Show connected render devices and how many are online/idle/busy. It is categorised as a Read tool in the Socheli MCP Server, which means it retrieves data without modifying state.
Register the Socheli MCP server in PolicyLayer and add a rule for socheli_fleet_status: 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 Socheli. Nothing to install.
socheli_fleet_status 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 socheli_fleet_status 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 socheli_fleet_status. 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.
socheli_fleet_status is provided by the Socheli MCP server (socheli/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 →