AI agents call account_config_status 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 tool queries and returns account configuration state without modifying, executing operations, or deleting data. It explicitly avoids exposing sensitive credentials (passwords). The read-only nature and lack of side effects classify it as a Read operation with low severity—misuse would only expose non-sensitive configuration details.
From the tool's definition Tool name 'account_config_status' and description '返回当前账号默认配置状态，不回显明文密码' (returns current account default configuration status, does not display plaintext passwords) indicate retrieval of account configuration information only.
Attacks that exploit this kind of access
返回当前账号默认配置状态，不回显明文密码。. 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 account_config_status: 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.
account_config_status 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 account_config_status 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 account_config_status. 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.
account_config_status 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 →