AI agents call fetch_data to retrieve information from Nornir without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name 'fetch_data' indicates a retrieval operation with no side effects. However, confidence is moderate (0.65) because the description is empty, making it impossible to confirm exact behavior. In a network infrastructure context, fetching data is typically read-only but could expose sensitive configuration or operational details, warranting medium severity.
From the tool's definition Tool named 'fetch_data' with empty description. The name suggests data retrieval. Given the server context (Nornir with NAPALM and Netmiko for network orchestration), this tool likely retrieves network device data, inventory, or operational state.
Attacks that exploit this kind of access
fetch_data. It is categorised as a Read tool in the Nornir MCP Server, which means it retrieves data without modifying state.
Register the Nornir MCP server in PolicyLayer and add a rule for fetch_data: 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 Nornir. Nothing to install.
fetch_data 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 fetch_data 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 fetch_data. 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.
fetch_data is provided by the Nornir MCP server (sydasif/nornir-mcp-server). 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 →