ssh_spawn
AI agents invoke ssh_spawn to trigger actions in Mcp Ssh Live. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The term 'spawn' in an SSH context strongly implies spawning a process or command on a remote system. The server description explicitly mentions 'spawning long-running remote commands,' and sibling tools like ssh_exec, ssh_run_persistent, and ssh_send_stdin confirm this is a remote code/command execution server. Executing arbitrary commands on a remote host carries critical blast radius.
From the tool's definition Tool name 'ssh_spawn' on a server described as enabling 'spawning long-running remote commands with live line-by-line output, signal handling, stdin input' — sibling tool 'ssh_exec' confirms remote command execution context.
Attacks that exploit this kind of access
ssh_spawn. It is categorised as a Execute tool in the Mcp Ssh Live MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Ssh Live MCP server in PolicyLayer and add a rule for ssh_spawn: 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_spawn is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the ssh_spawn 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_spawn. 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_spawn 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 →