Return aggregate session, thought, branch, quality, confidence, bias, mode, and step metrics.
AI agents call ultrabrain_metrics to retrieve information from Ultrabrain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and returns aggregate metrics about the current session. It is a read-only operation with no side effects, modifications, or destructive actions. Misuse potential is minimal as it only surfaces internal reasoning statistics.
From the tool's definition Return aggregate session, thought, branch, quality, confidence, bias, mode, and step metrics
Attacks that exploit this kind of access
Return aggregate session, thought, branch, quality, confidence, bias, mode, and step metrics. It is categorised as a Read tool in the Ultrabrain MCP Server, which means it retrieves data without modifying state.
Register the Ultrabrain MCP server in PolicyLayer and add a rule for ultrabrain_metrics: 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 Ultrabrain. Nothing to install.
ultrabrain_metrics 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 ultrabrain_metrics 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 ultrabrain_metrics. 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.
ultrabrain_metrics is provided by the Ultrabrain MCP server (lcv-ideas-software/ultrabrain-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 →