Open an SSH connection to a network device.
AI agents invoke connect_ssh to trigger actions in Network Device Assistant. 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 to a network device initiates an external network session and triggers real infrastructure interaction. It is not a passive read — it actively creates a persistent connection to potentially sensitive network equipment. This falls under Execute because it triggers an external operation (SSH session establishment) whose effects depend on arguments (host, credentials, port).
From the tool's definition 'Open an SSH connection to a network device'
Attacks that exploit this kind of access
Open an SSH connection to a network device. It is categorised as a Execute tool in the Network Device Assistant MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Network Device Assistant 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 Network Device Assistant. Nothing to install.
connect_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 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.
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.
connect_ssh is provided by the Network Device Assistant MCP server (mgarabito/network-device-mcp). 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 →