AI agents call get_system_overview to retrieve information from Mcp Ssh without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite empty description, the name and context suggest this tool queries/retrieves system status data without modifying anything. However, confidence is moderate (0.75) because the description is empty; if it unexpectedly triggers system changes or executes diagnostic commands with side effects, it could be Execute.
From the tool's definition Tool name 'get_system_overview' with context from sibling tools (analyze_log_errors, check_disk_health, check_high_load, check_network_connectivity, check_security, check_service_status) indicates retrieval of system information.
Attacks that exploit this kind of access
get_system_overview. It is categorised as a Read tool in the Mcp Ssh MCP Server, which means it retrieves data without modifying state.
Register the Mcp Ssh MCP server in PolicyLayer and add a rule for get_system_overview: 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 Mcp Ssh. Nothing to install.
get_system_overview 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_system_overview 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_system_overview. 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_system_overview is provided by the Mcp Ssh MCP server (zhouxiangjing/mcp-ssh). 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 →