This record as markdown: /tools/ikuai-mcp-server/enable-ssh.md
What enable_ssh does on Ikuai
AI agents invoke enable_ssh to trigger actions in Ikuai. 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 enable_ssh is rated High
Enabling or disabling SSH is an external system operation that changes the router's attack surface. Enabling SSH opens remote shell access to the device (high blast radius if misused by an AI agent), and disabling it could lock out administrators. This is an operational/service-control action best classified as Execute, with high severity due to the security implications of exposing or hiding SSH on a network device.
From the tool's definition 启用/禁用 SSH 服务 — enables or disables the SSH service on the router
Attacks that exploit this kind of access
The rule that runs enable_ssh safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ikuai, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For enable_ssh, this is the rule to start with:
enable_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.
The button opens the PolicyLayer dashboard: create your workspace, connect Ikuai, apply this rule, and every enable_ssh call is checked against it from then on.
Questions about enable_ssh
启用/禁用 SSH 服务. It is categorised as a Execute tool in the Ikuai MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ikuai MCP server in PolicyLayer and add a rule for enable_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 Ikuai. Nothing to install.
enable_ssh 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 enable_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.
Set action: deny in the PolicyLayer policy for enable_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.
enable_ssh is provided by the Ikuai MCP server (gxxHuang/ikuai-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ikuai, and thousands of servers like it.
Across the catalogue