Aggregate jurisdictional summary for a stack of providers: CLOUD Act exposure count, EU residency coverage, and missing DPAs. Maximum 50 providers per call.
AI agents call scan_stack to retrieve information from Sovereignty Scan without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
scan_stack retrieves and analyzes compliance metadata about provider stacks without creating, modifying, deleting, or executing any operations. It queries a compliance database and returns read-only summaries. No side effects, no data mutations, no code execution, no financial impact. This is a pure information-retrieval tool for compliance scanning.
From the tool's definition Tool performs scanning and aggregation of jurisdictional data with no modification capability: 'Aggregate jurisdictional summary', 'CLOUD Act exposure count', 'EU residency coverage', 'missing DPAs'. Returns summary information only.
Attacks that exploit this kind of access
Aggregate jurisdictional summary for a stack of providers: CLOUD Act exposure count, EU residency coverage, and missing DPAs. Maximum 50 providers per call. It is categorised as a Read tool in the Sovereignty Scan MCP Server, which means it retrieves data without modifying state.
Register the Sovereignty Scan MCP server in PolicyLayer and add a rule for scan_stack: 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 Sovereignty Scan. Nothing to install.
scan_stack 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 scan_stack 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 scan_stack. 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.
scan_stack is provided by the Sovereignty Scan MCP server (mightbesaad/sovereignty-scan-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 →