AI agents call list_examples to retrieve information from Netlab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and catalogs existing test topology data from netlab. It performs a query or enumeration of pre-existing resources without creating, modifying, executing, deleting, or committing financial actions. The blast radius of misuse is minimal—an agent cannot cause harm by listing available topologies.
From the tool's definition Tool name 'list_examples' and description 'Index netlab's integration test topologies' indicate a read-only indexing/listing operation with no modification or execution capability.
Attacks that exploit this kind of access
Index netlab's integration test topologies (real, maintained multi-platform scenarios). It is categorised as a Read tool in the Netlab MCP Server, which means it retrieves data without modifying state.
Register the Netlab MCP server in PolicyLayer and add a rule for list_examples: 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 Netlab. Nothing to install.
list_examples 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 list_examples 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 list_examples. 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.
list_examples is provided by the Netlab MCP server (steinzi/netlab-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 →