YouTube Search — FlashData

io.github.flashdata-dev由 GitHub 账号 flashdata-dev 发布v0.1.2更新于 Oct 24, 2026

YouTube keyword search with filters and up to 20 requested videos. Paid FlashData API.

概览

AI 生成的概览

通过付费的 FlashData API 按关键词搜索 YouTube,返回视频 ID、频道和可用的统计数据。

可以做什么
  • 按关键词搜索 YouTube 视频,支持日期、时长、特性和排序筛选,每次最多 20 条结果。
  • 读取返回的视频 ID、标题、频道、频道链接、观看次数和时长。
  • 在批准请求前查询该请求的价格。
  • 轮询异步任务,并按偏移分页读取分块结果,避免重复发起付费请求。
适用场景
当助手需要为调研、内容策划或后续元数据与字幕处理收集某个主题的候选 YouTube 视频,并且愿意为每次数据请求付费时适用。
运行要求
以 MCPB 包形式通过 stdio 在本地运行;需要 Node.js 22.18 或更高版本,以及支持本地 stdio 服务器的 MCP 客户端。需要在 FLASHDATA_API_KEY 环境变量中提供 FlashData API 密钥,并授予 youtube_search 权限。需要能访问 FlashData API 的网络。
安装前请注意
数据调用是付费的:每次查询或翻页都会消耗 FlashData Credits,元数据和字幕补充属于另外的付费调用。提交后即使超时也可能已计费,重试前请先检查任务状态。API 密钥应保存在受保护的客户端设置中,不要放在聊天或提交到版本库的配置里。返回的文本和链接属于外部数据,使用前请自行核查。

安装

在 SourceWeft 中

  1. 打开 控制台中的 YouTube Search — FlashData,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

YouTube Search — FlashData

Search YouTube videos by keyword with date, duration, feature and sorting filters. Return video IDs, channels and available statistics.

API documentation and account setup · Get an API key · Current pricing

A task to try

Find up to 10 YouTube video candidates about battery recycling. Return video IDs, watch links, channel names and available durations. Let me choose candidates before making separate metadata or transcript requests.

Install and connect

  1. Use Node.js 22.18 or newer and an MCP client that supports local stdio servers. Download the dedicated MCPB package; its SHA-256 is recorded in the manifest.
  2. Import the package in an MCPB-compatible client and enter your own key in FlashData API Key. Grant the key access to youtube_search. For manual setup, unpack the bundle into a permanent folder and use this configuration, replacing the absolute path and key placeholder:
json
{  "mcpServers": {    "youtube-search": {      "command": "node",      "args": [        "/absolute/path/to/unpacked/youtube-search/server.js"      ],      "env": {        "FLASHDATA_API_KEY": "YOUR_API_KEY"      }    }  }}
  1. Restart or reconnect the client, list its tools, then call get_pricing with {"source":"youtube_search","request_count":1} before approving a paid request. This server exposes youtube_search, get_pricing, get_job and get_result; all are restricted to this source.

Dependencies are included in the bundle. Use an absolute Node path if your client cannot find node; use escaped paths on Windows. Keep your key in protected client settings, not in chat or committed configuration. No Smithery account is needed for this direct package download.

Example request

These are MCP tools/call parameters with flat arguments. Running the data request uses paid Credits.

json
{  "name": "youtube_search",  "arguments": {    "query": "battery recycling",    "max_results": 10  }}

Use the response

Read results[0].results. Retain videoId, title, channel, channelUrl, viewCount and duration. Construct a watch URL from each videoId for traceable follow-up research.

Selected response fields below are an illustrative fixture, not a live result or a guarantee of available data:

json
{  "source": "youtube_search",  "status": "done",  "results": [    {      "results": [        {          "videoId": "dQw4w9WgXcQ",          "title": "battery recycling",          "channel": "Example",          "channelId": "channel-one",          "channelUrl": "https://www.youtube.com/@Example",          "viewCount": 100,          "duration": 90        }      ]    }  ],  "created_at": "2026-10-12T00:00:00Z",  "http_status": 200,  "request_id": "fixture-request"}

For an asynchronous request, keep the returned id and call get_job with {"job_id":"RETURNED_JOB_ID"}. Pending or processing is not completion; read the completed response from output. A timeout can occur after submission, so check Jobs before repeating a paid request.

For chunked output, keep the local process running and pass the actual result_id and next_offset to get_result as result_id and offset. Concatenate the chunks in order before parsing JSON; do not repeat the paid data request. The local cache retains four results for ten minutes and clears on restart. Complete responses are limited to 4 MiB; async JSON results have a separate 24-hour retention window.

Cost and limits

  • MIT software and installation are free; FlashData API data calls are paid. Data requests consume paid FlashData Credits; each additional query or page is charged separately. Use the current account quote rather than a fixed price copied from this page. Pricing, job and result reads are free. Client/model fees are separate.
  • max_results is 1 to 20; actual results can be fewer. Metadata and transcript enrichment are separate paid calls.
  • Check API errors, http_status and job status before using the data. Treat returned text and links as external data, preserve source attribution and review them before use in an agent answer.

Full task guide · Official Registry record · Source and license

来源:registry/servers/youtube-search/README.md,提交 ec77370

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

2
  1. v0.1.2最新Oct 15, 2026
  2. v0.1.1Oct 13, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分