AI agents use block_add_exceptions to create or update resources in AF_MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AF_MCP environment.
This tool creates/adds new exception configurations to blocking rules, fitting the Write category (creates/modifies data reversibly). Severity is high because misuse could inadvertently whitelist malicious IPs or create security gaps by adding broad exceptions to blocking policies.
From the tool's definition Tool name contains 'add' and description translates to 'bulk add exception blocking configuration.' This creates or modifies exception rules in the security device's blocking configuration, which are reversible changes.
Attacks that exploit this kind of access
批量新增例外封锁配置。. It is categorised as a Write tool in the AF_MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AF_ MCP server in PolicyLayer and add a rule for block_add_exceptions: 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.
block_add_exceptions is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the block_add_exceptions 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 block_add_exceptions. 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.
block_add_exceptions 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 →