connect_ssh · ContainerGuard MCP: Risk & Policy

WHAT IT DOES

What connect_ssh does on ContainerGuard MCP

AI agents invoke connect_ssh to trigger actions in ContainerGuard MCP. 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.

WHY IT NEEDS A POLICY

Why connect_ssh needs a policy

Establishing an SSH connection to a remote host is an active external operation that opens a persistent channel to a remote system. It is not merely reading data — it initiates a network session that can be used for further command execution. Combined with sibling tools like 'execute_command', misuse could lead to arbitrary remote code execution.

From the tool's definition 通过SSH连接到远程主机 (Connect to remote host via SSH)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

connect_ssh Rate-limited

connect_ssh stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "connect_ssh": {
      "limits": [
        {
          "counter": "connect_ssh_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches ContainerGuard MCP, so you can run agents against it safely.

FAQ

Questions about connect_ssh

What does the connect_ssh tool do? +

通过SSH连接到远程主机. It is categorised as a Execute tool in the ContainerGuard MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on connect_ssh? +

Register the ContainerGuard MCP server in PolicyLayer and add a rule for connect_ssh: 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 ContainerGuard MCP. Nothing to install.

What risk level is connect_ssh? +

connect_ssh is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit connect_ssh? +

Yes. Add a rate_limit block to the connect_ssh 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.

How do I block connect_ssh completely? +

Set action: deny in the PolicyLayer policy for connect_ssh. 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.

What MCP server provides connect_ssh? +

connect_ssh is provided by the ContainerGuard MCP server (rockmelodies/containerguardmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.