AI agents call network_bandwidth_test to retrieve information from Infra Ops without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool only reads/samples network statistics to measure throughput. It does not modify any data, execute commands with side effects, or make changes to infrastructure. The 1-second sampling interval confirms it is a passive observation operation. Severity is low as misuse only results in redundant metric collection.
From the tool's definition Measure current network throughput by sampling network stats over a 1 second interval
Attacks that exploit this kind of access
Measure current network throughput by sampling network stats over a 1 second interval. It is categorised as a Read tool in the Infra Ops MCP Server, which means it retrieves data without modifying state.
Register the Infra Ops MCP server in PolicyLayer and add a rule for network_bandwidth_test: 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 Infra Ops. Nothing to install.
network_bandwidth_test is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the network_bandwidth_test 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 network_bandwidth_test. 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.
network_bandwidth_test is provided by the Infra Ops MCP server (skyvanguard/infra-ops-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 →