// SCAN REPORT

Flash Cast

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

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

Last updated: 29 Jun 2026

7 can modify or destroy data

7 read-only

14 tools total

Community server · catalogue entry verified 29/06/2026

How to control Flash Cast ↓

TOOL MAP

What Flash Cast exposes to your agents

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

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Flash Cast tools

Execute · Medium analyze_douyin_video This tool takes a Douyin (TikTok) share link, fetches and analyzes the video content using AI compute, extracts scripts and structural patterns, and stores results into a project. Execute · Medium authenticate This tool triggers external operations: it opens a browser login page, forwards authentication requests to an external API endpoint, and automatically creates and saves an API Key upon success. Execute · High render_video The tool initiates a long-running external operation (2-10 minutes) combining text-to-speech, screen capture, and audio mixing. Write · Medium configure_voice_and_script This tool creates or modifies project metadata and rendering parameters (voice configuration, scripts, page marks, hold durations).

7 of Flash Cast's 14 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Flash Cast

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

Rate limit write operations

{
  "configure_voice_and_script": {
    "limits": [
      {
        "counter": "configure_voice_and_script_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_material_guidelines": {
    "limits": [
      {
        "counter": "get_material_guidelines_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 Flash Cast — 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 FLASH CAST →

Instant setup, no code required.

FULL CATALOGUE

All 14 Flash Cast tools

EXECUTE 3 tools

Execute analyze_douyin_video 分析抖音视频：输入分享链接，提取口播文案 + 爆款结构解析。结果存入项目。消耗 AI 算力，非订阅会员每项目上限 3 次。耗时约 35-130 秒。 Execute authenticate 校验 API Key 或打开本机登录页。未配置 Key 时浏览器访问本机 /auth，验证码与登录由 MCP 转发到 FLASH_CAST_API_BASE（默认 https://share.skyxhome.com）。 Execute render_video 触发视频渲染（TTS + 录屏 + 混音，约 2-10 分钟）。必须先 get_render_preview 并由用户确认；user_confirmed_content 必须为 true。返回 progressUrl 与

WRITE 4 tools

Write configure_voice_and_script 设置项目的配音配置、解说文案与声画同步 pageMarks；可选 page_holds：在某段 TTS 结束后插入「画面停留 + 可选旁白或静音」。若某项含可读 narration：对该文案单独 TTS，音长以实测为准（ Write create_project 创建一个新的视频项目，返回 projectId。后续所有操作都基于此 projectId。触发会员/试用检查。 Write upload_html 上传 HTML 内容到项目。支持直接传入 HTML 字符串或本地文件路径。返回幻灯片数量、每页文本摘要和结构性警告。 Write upload_material 上传图片或视频到 OSS，返回 ossKey、signedUrl（默认可为公网直链，字段名不变）、时长与「时间轴/原声」提示。视频在后端会转码为 H.264 MP4（便于录屏解码），写入 HTML 时 src 用返回的

READ 7 tools

Read get_material_guidelines 读取平台对嵌入 HTML 的素材时长、pageMarks 与「视频原声」的约定说明（无需上传）。生成 HTML / 划分 pageMarks 前应先调用。 Read get_render_preview 渲染前必须：拉取当前项目的 HTML 与配音文案等摘要，并返回本机只读预览页 URL。请先让用户在浏览器打开 previewUrl 核对；用户口头确认无误后，再在 render_video 中传入 user_confir Read get_render_status 查询渲染状态。渲染中返回进度百分比和步骤描述；完成后返回视频下载链接。建议每 15 秒轮询一次。 Read get_template_detail （可选）获取某个内置模板的规范与示例，仅在用户希望基于模板生成 HTML 时调用；非流程必需步骤。 Read list_templates （可选）列出平台内置 HTML 视频模板，供需要「参考版式」时使用。用户也可完全不用模板、自行提供任意符合闪映规范的 HTML。 Read list_voices 返回所有可用配音音色，含 id、name、gender、trait（特质描述）、description、tags、suggestedFor 等元数据。AI 据此自动匹配最适合内容调性的音色。 Read re_render_video 强制重新渲染视频（会扣除额度）。当用户修改了 HTML 素材、配音文案或音色后需要重新生成，或者对上一次渲染结果不满意想要重做时使用。调用前必须明确告知用户：此操作将消耗 1 次渲染额度。如果项目当前正在渲染中则拒绝（须

FAQ

Questions about Flash Cast

How do I prevent bulk modifications through Flash Cast? +

The Flash Cast server has 4 write tools including configure_voice_and_script, create_project, upload_html. 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 Flash Cast.

How many tools does the Flash Cast MCP server expose? +

14 tools across 2 categories: Read, Write. 7 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Flash Cast? +

Register the Flash Cast 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 Flash Cast tool call.

Deterministic rules across all 14 Flash Cast tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON FLASH CAST →

Instant setup, no code required.

14 Flash Cast tools catalogued and risk-classified — across an index of 43,000+ MCP servers.