AI agents call get_action_detail 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 retrieves historical information about a single action including pre-state snapshots, device responses, and audit trail. It performs read-only lookups with no capability to modify, delete, execute, or affect financial systems. The context of an AF security device management server confirms it retrieves audit and status information rather than modifying device behavior.
From the tool's definition Tool name 'get_action_detail' and description '查询单个 action 的完整详情（含 pre_state 快照 + 设备响应 + 审计链）' indicates retrieval/querying of action details, snapshots, device responses, and audit chain.
Attacks that exploit this kind of access
查询单个 action 的完整详情（含 pre_state 快照 + 设备响应 + 审计链）。. 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_action_detail: 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_action_detail 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_action_detail 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_action_detail. 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_action_detail 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 →