pt_send_raw
AI agents invoke pt_send_raw to trigger actions in MCP Packet Tracer. 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.
On a Cisco Packet Tracer server designed to send IOS commands to network devices, a 'send_raw' tool almost certainly executes arbitrary raw commands against network devices. This falls under Execute (potentially Destructive) as it could run any IOS command including those that delete configs or disrupt network topology.
From the tool's definition Tool name 'pt_send_raw' on a server that 'configure devices with IOS commands' and 'control network topologies'. The 'raw' suffix strongly implies sending arbitrary/unfiltered commands.
Attacks that exploit this kind of access
pt_send_raw. It is categorised as a Execute tool in the MCP Packet Tracer MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Packet Tracer MCP server in PolicyLayer and add a rule for pt_send_raw: 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 Packet Tracer. Nothing to install.
pt_send_raw 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 pt_send_raw 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 pt_send_raw. 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.
pt_send_raw is provided by the MCP Packet Tracer MCP server (mainorcruz/mcp_packet_tracer). 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 →