切会话模式:
AI agents use agent_set_mode to create or update resources in Frx Director — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Frx Director environment.
The tool appears to change/set a mode for an agent session, which is a configuration modification. This is reversible (modes can be switched back), placing it in Write. Description is very brief and in Chinese, lowering confidence. Severity is medium as changing agent operating mode could affect behavior of the browser reverse-engineering agent.
From the tool's definition Tool name 'agent_set_mode' and description '切会话模式' (which translates to 'switch session mode')
Attacks that exploit this kind of access
切会话模式:. It is categorised as a Write tool in the Frx Director MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Frx Director MCP server in PolicyLayer and add a rule for agent_set_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 Frx Director. Nothing to install.
agent_set_mode 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 agent_set_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 agent_set_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.
agent_set_mode is provided by the Frx Director MCP server (whitenightshadow/frx-director-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 →