Check if authorized with a merchant domain
AI agents call scp_check_authorization to retrieve information from SCP Local MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a read-only check of authorization status. It does not create, modify, delete, or execute actions; it simply queries whether authorization exists with a given merchant domain. This is consistent with the Read category (retrieves or queries data; no side effects).
From the tool's definition Tool name is 'scp_check_authorization' and description states it 'Check if authorized with a merchant domain' — this is a query operation that retrieves authorization status without modifying state or triggering external operations.
Attacks that exploit this kind of access
Check if authorized with a merchant domain. It is categorised as a Read tool in the SCP Local MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SCP Local MCP Server MCP server in PolicyLayer and add a rule for scp_check_authorization: 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 SCP Local MCP Server. Nothing to install.
scp_check_authorization 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 scp_check_authorization 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 scp_check_authorization. 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.
scp_check_authorization is provided by the SCP Local MCP Server MCP server (shopper-context-protocol/scp-mcp-wrapper). 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 →