cx_show
Run 'show' commands on a CX switch (all must start with 'show ', max 20, async polls ~60s).
This record as markdown: /tools/hpe-networking-mcp/cx-show.md
What cx_show does on Hpe Networking
AI agents invoke cx_show to trigger actions in Hpe Networking. 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 cx_show is rated High
Although 'show' commands are typically read-only in network CLI contexts, this tool *executes* commands on a live CX switch via an async polling mechanism. The act of running commands on a network device is an Execute-category action.
From the tool's definition 'Run show commands on a CX switch' — executes commands on a live network device; triggers external operations on network infrastructure
Attacks that exploit this kind of access
The rule that runs cx_show safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Hpe Networking, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For cx_show, this is the rule to start with:
cx_show 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 Hpe Networking, apply this rule, and every cx_show call is checked against it from then on.
Questions about cx_show
Run 'show' commands on a CX switch (all must start with 'show ', max 20, async polls ~60s). It is categorised as a Execute tool in the Hpe Networking MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Hpe Networking MCP server in PolicyLayer and add a rule for cx_show: 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 Hpe Networking. Nothing to install.
cx_show 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 cx_show 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 cx_show. 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.
cx_show is provided by the Hpe Networking MCP server (secure-ssid/hpe-networking-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Hpe Networking, and thousands of servers like it.
Across the catalogue