AI agents call render_config 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 generates configuration output from existing topology data without modifying state, creating resources, executing external code, or affecting infrastructure. It is a read-only operation that transforms and presents data. The 'offline' qualifier further confirms no external systems are contacted or altered.
From the tool's definition Tool description states 'Render real per-device config from a netlab topology — offline, no containers.' The verb 'render' and 'offline' operation indicate data retrieval and formatting without side effects.
Attacks that exploit this kind of access
Render real per-device config from a netlab topology — offline, no containers. 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 render_config: 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.
render_config 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 render_config 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 render_config. 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.
render_config 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 →