Fieldscribe

io.github.CloudCorpRecords由 GitHub 账号 CloudCorpRecords 发布v0.1.0更新于 Nov 7, 2026

Transcribe public audio and video URLs to clean text and SRT, with job tracking.

已验证STDIO仅桌面效率与工作流媒体与设计

概览

AI 生成的概览

本地桥接工具,连接托管转写服务,把公开的音视频链接转成文本或 SRT,并跟踪任务进度。

可以做什么
  • 提交公开的视频或音频链接进行逐字转写,立即返回任务 ID
  • 查询任务状态与元数据,并在完成后获取完整转写文本
  • 按时间倒序列出账户下的所有转写任务
  • 永久删除已完成或出错的任务及其存储的文本
适用场景
适合让助手在不离开对话的情况下,把公开的 YouTube 视频、播客或讲座录音转成文字,并在之后跟踪或清理这些任务。
运行要求
以 stdio 本地进程运行,可通过 npx 或 Docker 镜像启动;需要能访问上游转写服务的网络。可选设置 FIELDTRANSCRIPT_MCP_URL 覆盖上游地址,设置 FIELDTRANSCRIPT_API_KEY 以上游发送 Bearer 令牌;未设置密钥时不发送认证头。
安装前请注意
提交会在调用者账户上创建任务,可能消耗该账户的配额或额度。delete_job 会永久删除已完成任务及其存储文本,无法撤销。提交的链接会被转发给第三方托管服务,请勿使用私有或内部链接。若设置了 API 密钥,该密钥会发送到上游地址。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Fieldscribe,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

fieldscribe

fieldscribe is a small local bridge to FieldTranscript's hosted MCP server, a transcription service that turns public audio and video files into text. You hand it a URL — a YouTube video, a podcast episode, a lecture recording — and it runs the transcription as a job in the background: submitting returns a job id immediately, the job takes roughly one to ten minutes, and polling the job eventually yields the finished transcript as clean text or SRT, depending on what the upstream returns.

The bridge keeps no transcripts and no job state of its own. It serves the upstream server's tool list locally, exactly as captured from the live endpoint, and forwards each tool call upstream, returning the result untouched. One tool in the captured surface deletes — delete_job permanently removes a finished job and its stored text — and one creates work: submit_transcription starts a new transcription job on the caller's account. Everything else reads.

Tools

  • submit_transcription — submit a public video or audio URL (YouTube etc.) for verbatim transcription. Returns a job_id immediately. Required: url. Transcription takes about 1-10 minutes; poll get_job every 30-60 seconds until the status is done. Not for private or internal URLs.
  • get_job — check one transcription job: its status (queued, working, done or error) and metadata. Required: job_id. Optional: include_transcript (default false) — set it only once the status is done and the full text is actually needed, because transcripts of long videos are large.
  • list_jobs — list all transcription jobs on your account, newest first. No arguments.
  • delete_job — permanently delete a finished (done or errored) transcription job and its stored text. Required: job_id. Refused while the job is queued or running, and it cannot be undone.

Configuration

  • FIELDTRANSCRIPT_MCP_URL (optional) — override the upstream endpoint. Defaults to https://mcp.fieldtranscript.com/mcp. (The override hook is this rebuild's own labelled reconstruction.)
  • FIELDTRANSCRIPT_API_KEY (optional) — when set, every upstream request carries an Authorization: Bearer <key> header. When it is not set, no auth header is sent. (This forwarding is also a labelled reconstruction; the original surface was captured keyless.)

Forwarding mechanics

On the first tool call the client opens a streamable HTTP session with the upstream: a JSON-RPC initialize request (protocolVersion 2025-03-26, clientInfo name fieldscribe), then a notifications/initialized notification, then the tools/call request carrying the caller's arguments unchanged. When the upstream answers initialize with an Mcp-Session-Id header, that value rides on every later request of the session, which is reused for the life of the process. Replies may arrive as plain JSON or as server-sent events; both are read.

Successful upstream results pass through verbatim, including any isError flag the upstream sets. Failures — a JSON-RPC error, a non-2xx status, an unreadable response, or a request that cannot be completed — come back as an isError result whose text starts with fieldscribe error: (this rendering is this rebuild's own labelled reconstruction).

CLI

Each tool is also a subcommand taking one JSON argument string (omit it for tools that take none):

bash
npx @reneturcios/fieldscribe submit_transcription '{"url":"https://www.youtube.com/watch?v=abc123"}'npx @reneturcios/fieldscribe get_job '{"job_id":"job-7"}'npx @reneturcios/fieldscribe get_job '{"job_id":"job-7","include_transcript":true}'npx @reneturcios/fieldscribe list_jobsnpx @reneturcios/fieldscribe delete_job '{"job_id":"job-7"}'npx @reneturcios/fieldscribe --version

Exit codes: 0 on success, 1 on an isError result, 2 on a usage error.

MCP server

bash
npx -y @reneturcios/fieldscribe mcp

MCP client config:

json
{  "mcpServers": {    "fieldscribe": {      "command": "npx",      "args": ["-y", "@reneturcios/fieldscribe", "mcp"]    }  }}

Docker

bash
docker run -i ghcr.io/cloudcorprecords/fieldscribedocker run --rm ghcr.io/cloudcorprecords/fieldscribe --version

The container's default command is mcp, so the first form is a stdio MCP server; any other arguments reach the CLI normally.

Development

bash
npm installnpm run buildnpm testnpm run dev

The test suite runs entirely against a stubbed JSON-RPC upstream — no live network calls.

License

MIT — see LICENSE.

来源:README.md,提交 0a863af

工具

4

submit_transcription

Submit a public video or audio URL (YouTube etc.) for verbatim transcription. Returns a job_id immediately. Transcription takes ~1-10 minutes: poll get_job with the job_id every 30-60 seconds until status is 'done', then call get_job with include_transcript=true. Not for private/internal URLs.

输入参数url必填

get_job

Check a transcription job. Returns status (queued / working / done / error) and metadata. Set include_transcript=true only once status is 'done' and you actually need the full text in context - transcripts of long videos are large.

输入参数job_id必填include_transcript

list_jobs

List all transcription jobs on your account, newest first.

无需输入参数。

delete_job

Permanently delete a finished (done or errored) transcription job and its stored text. Refused while the job is queued or running. This cannot be undone.

输入参数job_id必填

版本历史

1
  1. v0.1.0最新Nov 5, 2026

评分

已满足适用检查项的 90%

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
  • 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。

  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分