AI agents call check_drift to retrieve information from Odgs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Without an explicit description, the name 'check_drift' most likely indicates a monitoring or detection function that compares states rather than modifying them. However, confidence is reduced due to the empty description—the tool could theoretically trigger corrective actions or enforcement measures if drift is detected, which might elevate it to Execute.
From the tool's definition Tool name 'check_drift' with no description provided. In governance/compliance contexts, 'drift' checking typically refers to detecting deviations or divergences between current state and expected state—a read-only diagnostic operation.
Attacks that exploit this kind of access
check_drift. It is categorised as a Read tool in the Odgs MCP Server, which means it retrieves data without modifying state.
Register the Odgs MCP server in PolicyLayer and add a rule for check_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 Odgs. Nothing to install.
check_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 check_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 check_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.
check_drift is provided by the Odgs MCP server (metricprovenance/odgs-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 →