AI agents call get_confirm_mode to retrieve information from AF_MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only query tool that retrieves the current confirmation mode setting. It has no side effects—it merely checks configuration state to inform downstream decision-making about how other operations will be processed. No data is created, modified, deleted, or executed as a result of calling this tool. Severity is low because even if misused, reading a configuration setting poses minimal risk on its own.
From the tool's definition Tool name 'get_confirm_mode' and description indicate it 'returns the current effective confirmation mode' to determine how high-risk write operations are handled (manual vs automatic).
Attacks that exploit this kind of access
返回当前有效的确认模式，用于判断高风险写操作按 手动 还是 自动 处理。. It is categorised as a Read tool in the AF_MCP MCP Server, which means it retrieves data without modifying state.
Register the AF_ MCP server in PolicyLayer and add a rule for get_confirm_mode: 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 AF_MCP. Nothing to install.
get_confirm_mode 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 get_confirm_mode 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 get_confirm_mode. 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.
get_confirm_mode is provided by the AF_ MCP server (xiaqijun/af_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 →