Connect to an SSH server
AI agents invoke ssh_connect to trigger actions in MCP SSH Server. 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.
Initiating an SSH connection is an active external operation that opens a channel to a remote server. It is not merely reading data; it triggers a network connection and authentication handshake on a remote system. Combined with sibling tools like ssh_execute and ssh_docker_deploy, a misused connection could be the entry point for high-impact remote operations.
From the tool's definition 'Connect to an SSH server' — establishes a remote SSH connection to an external system
Attacks that exploit this kind of access
Connect to an SSH server. It is categorised as a Execute tool in the MCP SSH Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP SSH Server 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 MCP SSH Server. 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 MCP SSH Server MCP server (mahathirmuh/mcp-ssh-server). 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 →