AI agents call ops_metrics to retrieve information from Git Steer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries operational metrics without causing side effects, state changes, or triggering external operations. It is purely informational, making it a Read category risk with low severity since exposure would only leak performance data without enabling destructive or financial actions.
From the tool's definition Tool description explicitly states 'Get operational metrics' with read-only operations: 'alert frequency', 'mean time to remediation', 'auto-merge success rate', and 'PR dedup hit rate'. No modification, deletion, or execution of external operations occurs.
Attacks that exploit this kind of access
Get operational metrics: alert frequency, mean time to remediation, auto-merge success rate, and PR dedup hit rate. It is categorised as a Read tool in the Git Steer MCP Server, which means it retrieves data without modifying state.
Register the Git Steer MCP server in PolicyLayer and add a rule for ops_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 Git Steer. Nothing to install.
ops_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 ops_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 ops_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.
ops_metrics is provided by the Git Steer MCP server (ry-ops/git-steer). 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 →