Connect to a Linux host via SSH using credentials from config.yaml. Use the host alias (e.g.,
AI agents invoke ssh_connect to trigger actions in SSH Linux Control. 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.
Establishing an SSH connection initiates an authenticated remote session to a Linux host, enabling subsequent command execution. While the connection itself doesn't execute destructive commands, it opens a privileged execution channel on a remote system. Given that sibling tools (ssh_execute) can run arbitrary commands via this connection, and the server supports sudo operations, the blast radius of misuse is high.
From the tool's definition Connect to a Linux host via SSH using credentials from config.yaml
Attacks that exploit this kind of access
Connect to a Linux host via SSH using credentials from config.yaml. Use the host alias (e.g.,. It is categorised as a Execute tool in the SSH Linux Control MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the SSH Linux Control MCP server in PolicyLayer and add a rule for ssh_connect: 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 Linux Control. Nothing to install.
ssh_connect 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_connect 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_connect. 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_connect is provided by the SSH Linux Control MCP server (yutooop/mcp_linux_administration_ssh-openwebui_tool). 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 →