ssh_persistent_status
AI agents call ssh_persistent_status to retrieve information from Mcp Ssh Live without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve status information about persistent SSH jobs or connections without modifying, executing new commands, or deleting anything. However, confidence is moderated because the description is empty, and in the context of an SSH/remote execution server, status queries could theoretically expose sensitive operational information (timing, process IDs, running commands).
From the tool's definition Tool name 'ssh_persistent_status' suggests status querying of persistent SSH connections; sibling tool 'ssh_list_jobs' and 'ssh_run_persistent' indicate a job-management system where status retrieval is a read operation.
Attacks that exploit this kind of access
ssh_persistent_status. It is categorised as a Read tool in the Mcp Ssh Live MCP Server, which means it retrieves data without modifying state.
Register the Mcp Ssh Live MCP server in PolicyLayer and add a rule for ssh_persistent_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 Mcp Ssh Live. Nothing to install.
ssh_persistent_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 ssh_persistent_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 ssh_persistent_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.
ssh_persistent_status is provided by the Mcp Ssh Live MCP server (pmboxbiz/mcp-ssh-live). 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 →