Connect to SSH server using saved credentials
AI agents invoke ssh_connect_with_credential 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.
Establishing an SSH connection initiates an active session to a remote server, which is an external operation with significant side effects. Once connected, subsequent commands can be executed on the remote system. This goes beyond a simple read/write operation — it triggers an external network operation and opens a persistent channel that can be leveraged for arbitrary remote execution.
From the tool's definition Connect to SSH server using saved credentials
Attacks that exploit this kind of access
Connect to SSH server using saved credentials. 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_with_credential: 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_with_credential 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_with_credential 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_with_credential. 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_with_credential 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 →