Compare configurations in your repository with what is actually deployed in the cluster. By default, automatically fixes drift by recreating missing config files.
AI agents call arc_detect_drift to retrieve information from ARC Config MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though arc_detect_drift only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Compare configurations in your repository with what is actually deployed in the cluster. By default, automatically fixes drift by recreating missing config files. It is categorised as a Read tool in the ARC Config MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ARC Config MCP Server MCP server in PolicyLayer and add a rule for arc_detect_drift: 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 ARC Config MCP Server. Nothing to install.
arc_detect_drift 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 arc_detect_drift 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 arc_detect_drift. 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.
arc_detect_drift is provided by the ARC Config MCP Server MCP server (tsviz/arc-config-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 →