AI agents call nia_stats to retrieve information from Nia Link without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns metrics about system usage. It performs no actions that create, modify, delete, or execute anything. The scope is limited to reading pre-computed or logged statistics. While the parent server (nia-link) has Execute-category capabilities (nia_interact, nia_workflow), this specific tool is a simple monitoring/telemetry read operation with minimal security risk.
From the tool's definition Tool description states it retrieves 'usage statistics including request counts, tokens saved, response times, and error rates' — purely informational data retrieval with no modification, execution, or side effects.
Attacks that exploit this kind of access
Get Nia-Link usage statistics including request counts, tokens saved, response times, and error rates. It is categorised as a Read tool in the Nia Link MCP Server, which means it retrieves data without modifying state.
Register the Nia Link MCP server in PolicyLayer and add a rule for nia_stats: 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 Nia Link. Nothing to install.
nia_stats 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 nia_stats 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 nia_stats. 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.
nia_stats is provided by the Nia Link MCP server (nia-atavism/nia-link). 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 →