读 worker 的阶段结论(①发现 ②2-3 方向 ③推荐)给 director 评判:含完整 content 尾、步骤尾、工作目录 progress.md/ledger.md(worker 真正依赖的持久知识),以及 ★driftHint + runlogTail——
AI agents call agent_read to retrieve information from Frx Director without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure data retrieval operation. The tool queries the state and results of a worker agent's progress, including persistent knowledge files and logs. It has no side effects—no code execution, no data modification, and no external operations triggered. The worst outcome of misuse would be the director seeing stale or incorrect status information, which is a low-severity information disclosure risk.
From the tool's definition The tool name is 'agent_read' and the description indicates it 'reads' (读) worker's phase conclusions, stage results, work directory files (progress.md/ledger.md), and log tails.
Attacks that exploit this kind of access
读 worker 的阶段结论(①发现 ②2-3 方向 ③推荐)给 director 评判:含完整 content 尾、步骤尾、工作目录 progress.md/ledger.md(worker 真正依赖的持久知识),以及 ★driftHint + runlogTail——. It is categorised as a Read tool in the Frx Director MCP Server, which means it retrieves data without modifying state.
Register the Frx Director MCP server in PolicyLayer and add a rule for agent_read: 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_read 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 agent_read 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_read. 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_read 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 →