Given a list of file paths (typically the files a PR touches), return the knowledge entries that reference them. Use at PR time to flag potentially stale entries.
AI agents call check_drift to retrieve information from Domain memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query against a knowledge base to identify cross-references. It has no side effects, does not modify state, and poses minimal risk even if invoked with arbitrary file paths. The worst outcome is retrieving unexpected or voluminous results, which does not constitute a security violation.
From the tool's definition The tool 'check_drift' returns knowledge entries that reference given file paths; it queries and retrieves data without modifying, deleting, or executing anything.
Attacks that exploit this kind of access
Given a list of file paths (typically the files a PR touches), return the knowledge entries that reference them. Use at PR time to flag potentially stale entries. It is categorised as a Read tool in the Domain memory MCP Server, which means it retrieves data without modifying state.
Register the Domain memory 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 Domain memory. 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 Domain memory MCP server (mashware/domain-memory). 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 →