对赛狐 API 做最小烟测：在线产品 → 订单 → 销售数据 → 评价。
AI agents call sellfox_smoke_check to retrieve information from Sellfox MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves data through a series of read-only API queries to verify connectivity and basic functionality. It does not create, modify, delete, or execute any code—it merely samples existing data endpoints for health-check purposes. This is a diagnostic/monitoring operation with no side effects, squarely fitting the Read category.
From the tool's definition Tool performs a smoke test that queries API endpoints in sequence: 'online products → orders → sales data → reviews'. No modification, deletion, or execution of external operations occurs.
Attacks that exploit this kind of access
对赛狐 API 做最小烟测：在线产品 → 订单 → 销售数据 → 评价。. It is categorised as a Read tool in the Sellfox MCP MCP Server, which means it retrieves data without modifying state.
Register the Sellfox MCP server in PolicyLayer and add a rule for sellfox_smoke_check: 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 Sellfox MCP. Nothing to install.
sellfox_smoke_check 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 sellfox_smoke_check 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 sellfox_smoke_check. 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.
sellfox_smoke_check is provided by the Sellfox MCP server (shuolol/sellfox-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 →