TranscriptionTools MCP Server

Name: TranscriptionTools MCP Server
Author: MushroomFleet

@MushroomFleet

代码仓库

关于 TranscriptionTools MCP Server

MCP server for transcript processing — formatting, contextual repair & smart summarization with deep-thinking LLMs

#transcription #transcript-processing #smart-summarization

基本信息

分类

其他

许可证

MIT

运行时

node

传输方式

stdio

发布者

MushroomFleet

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "TranscriptionTools-MCP": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "@MushroomFleet/transcriptiontools-mcp",
        "--client",
        "claude"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is TranscriptionTools MCP Server?

TranscriptionTools MCP Server is a Model Context Protocol server that provides intelligent transcript processing, including natural formatting, contextual repair, and smart summarization powered by Deep Thinking LLMs. It is aimed at users needing to clean, format, and summarize spoken-language transcripts.

How to use TranscriptionTools MCP Server?

Install by cloning the repository, running npm install and npm run build, then configure the server in your MCP settings file. Invoke the tools repair_text, get_repair_log, format_transcript, and summary_text via the MCP client interface.

Key features of TranscriptionTools MCP Server

Four MCP tools for transcript processing: repair, log, format, summary
repair_text corrects transcription errors with >90% confidence
format_transcript removes timestamps and applies intelligent spacing
summary_text generates summaries with time, word, or character constraints
get_repair_log retrieves detailed logs of previous repairs

Use cases of TranscriptionTools MCP Server

Correcting errors and awkward phrasing in raw automated transcripts
Converting timestamped meeting or interview transcripts into natural prose
Generating concise, constraint-based summaries of lengthy transcriptions
Auditing all changes made during a repair session via repair logs

FAQ from TranscriptionTools MCP Server

What are the system requirements?

Node.js and npm are required to build and run the server. The server is written in TypeScript and compiles to JavaScript.

What runtime or LLM does it depend on?

The README mentions “Deep Thinking LLMs” but does not specify a particular model or API; the server appears to use its own logic for repair and formatting without requiring an external LLM service.

Where does transcript data live?

Data is passed directly as input text or file paths; the server does not store transcripts externally unless the user provides file paths on the local filesystem.

What transport or authentication does it use?

The server uses standard MCP stdio transport; no authentication or remote endpoints are described in the README.

Does it ever modify the original audio?

No. The contextual repair feature explicitly states “No original audio required” – it works only on the text transcript.

其他分类下的更多 MCP 服务器

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K