AI agents call search_logs to retrieve information from Ssh without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries log file data from a remote system via SSH. While it is fundamentally a Read operation (no data is modified or deleted), the severity is elevated to medium because: (1) logs may contain sensitive information (credentials, private data, system details), (2) it operates on a remote system with potentially privileged access, and (3) an agent could systematically extract confidential logs.
From the tool's definition Tool name is 'search_logs' and description states it 'Search log files from the current remote shell state' — a retrieval operation with no modification or deletion capability mentioned.
Attacks that exploit this kind of access
Search log files from the current remote shell state. It is categorised as a Read tool in the Ssh MCP Server, which means it retrieves data without modifying state.
Register the Ssh MCP server in PolicyLayer and add a rule for search_logs: 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 Ssh. Nothing to install.
search_logs 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 search_logs 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 search_logs. 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.
search_logs is provided by the Ssh MCP server (sc-ml-cmd/ssh-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 →