// SCAN REPORT

Frx Director

11 tools. 7 can modify or destroy data without limits.

7 write tools that can modify data. Rate limits recommended.

Last updated: 2 Jul 2026

7 can modify or destroy data

4 read-only

11 tools total

Community server · catalogue entry verified 02/07/2026

How to control Frx Director ↓

TOOL MAP

What Frx Director exposes to your agents

Read (4) Write / Execute (7) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Frx Director tools

Execute · High agent_call_tool This tool allows a director model to directly execute browser engine tools without intermediary validation or constraints. Execute · High agent_start This tool triggers the start of a reverse-engineering agent session with significant capabilities including browser navigation, directory creation, and autonomous model execution. Execute · High agent_stop While the tool itself is a control/termination command rather than destructive (progress is persisted), it executes an action that interrupts an external agent's behavior. Execute · High agent_tools This tool enables execution of powerful reverse-engineering operations against web pages and browser internals.

7 of Frx Director's 11 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Frx Director

PolicyLayer is an MCP gateway — it sits between your AI agents and Frx Director, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "agent_set_mode": {
    "limits": [
      {
        "counter": "agent_set_mode_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "agent_read": {
    "limits": [
      {
        "counter": "agent_read_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Frx Director — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON FRX DIRECTOR →

Instant setup, no code required.

FULL CATALOGUE

All 11 Frx Director tools

EXECUTE 6 tools

Execute agent_call_tool ★你(director)亲自跑一个浏览器引擎工具,跳过 DeepSeek worker —— 强模型直驱引擎级工具,比委派 worker 磨更快更准。 Execute agent_send ★director 的核心动作:把方向纠正作为下一条 user 消息发出去并起下一轮(=harness 的 advance)。 Execute agent_start 开一个新的逆向会话:配置 worker 模型(默认沿用浏览器里已配的)+关掉工具确认门、(可选)导航到目标 URL、建工作目录、用便宜的 worker 模型以【AI 辅助模式】发出第一轮(task 作为第 0 条 use Execute agent_stop 砍掉 worker 当前这一轮(agentSession.stop)。用在:读到快照发现 worker 正冲向错误路线,想立刻截停并 agent_send 纠正、不想干等它 settle。进展已落盘(ledger/pro Execute agent_tools 列出浏览器侧可用的逆向工具清单(名称/说明/是否需确认/参数名)——含 16 个引擎级逆向工具(signer_trace/jsvmp_trace/closure_read/webapi_trace/whitebox_di Execute agent_wait_for_stop 阻塞轮询直到 worker 这一轮 settled(阶段门到了)。这是

WRITE 1 tools

Write agent_set_mode 切会话模式:

READ 4 tools

Read agent_read 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 Read agent_runlog 引擎级 run 日志(getRunLog):请求/响应时序、重试、idle 看门狗超时、finishReason、drift 检测。诊断用——让 director 区分 Read agent_state 廉价的存活/进度快照(比 agent_read 轻):running/settled/nSteps/checkpointSeq/错误/contentTail 短尾/driftHint。 Read frx_status ★开跑前先调这个自检:浏览器(marionette)连没连、当前 worker provider/model、worker key 配没配。

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Frx Director

How do I prevent bulk modifications through Frx Director? +

The Frx Director server has 1 write tools including agent_set_mode. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Frx Director.

How many tools does the Frx Director MCP server expose? +

11 tools across 3 categories: Execute, Read, Write. 4 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Frx Director? +

Register the Frx Director MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Frx Director tool call.

Deterministic rules across all 11 Frx Director tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON FRX DIRECTOR →

Instant setup, no code required.

11 Frx Director tools catalogued and risk-classified — across an index of 43,000+ MCP servers.