TranscriptionTools
An MCP server for intelligent transcript processing, including formatting, repair, and summarization.
TranscriptionTools MCP Server
An MCP server providing intelligent transcript processing capabilities, featuring natural formatting, contextual repair, and smart summarization powered by Deep Thinking LLMs.
Available MCP Tools
This MCP server exposes four powerful tools for transcript processing:
- repair_text - Analyzes and repairs transcription errors with greater than 90% confidence
- get_repair_log - Retrieves detailed analysis logs from previous repairs
- format_transcript - Transforms timestamped transcripts into naturally formatted text
- summary_text - Generates intelligent summaries using ACE cognitive methodology
Installation
Installing via Smithery
To install Transcription Tools for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @MushroomFleet/transcriptiontools-mcp --client claude
- Clone this repository:
git clone https://github.com/mushroomfleet/TranscriptionTools-MCP
cd TranscriptionTools-MCP
- Install dependencies:
npm install
- Build the server:
npm run build
- Configure the MCP server in your MCP settings file:
{
"mcpServers": {
"transcription-tools": {
"command": "node",
"args": ["/path/to/TranscriptionTools-MCP/build/index.js"],
"disabled": false,
"autoApprove": []
}
}
}
Using the MCP Tools
Repairing Transcription Errors
<use_mcp_tool>
<server_name>transcription-tools</server_name>
<tool_name>repair_text</tool_name>
<arguments>
{
"input_text": "We recieve about ten thousand dollars which is defiantly not enough.",
"is_file_path": false
}
</arguments>
</use_mcp_tool>
Formatting Timestamped Transcripts
<use_mcp_tool>
<server_name>transcription-tools</server_name>
<tool_name>format_transcript</tool_name>
<arguments>
{
"input_text": "/path/to/timestamped-transcript.txt",
"is_file_path": true,
"paragraph_gap": 8,
"line_gap": 4
}
</arguments>
</use_mcp_tool>
Generating Summaries
<use_mcp_tool>
<server_name>transcription-tools</server_name>
<tool_name>summary_text</tool_name>
<arguments>
{
"input_text": "Long text to summarize...",
"is_file_path": false,
"constraint_type": "words",
"constraint_value": 100
}
</arguments>
</use_mcp_tool>
Retrieving Repair Logs
<use_mcp_tool>
<server_name>transcription-tools</server_name>
<tool_name>get_repair_log</tool_name>
<arguments>
{
"session_id": "20241206143022"
}
</arguments>
</use_mcp_tool>
Core Technologies
Natural Formatting
- Removes timestamps while preserving speech patterns
- Applies intelligent spacing based on pause duration
- Respects natural grammar and language flow
- Maintains exact transcribed content
Contextual Repair
- Identifies and corrects likely transcription errors
- Uses semantic context for high-confidence corrections
- Maintains detailed logs of all changes
- 90% confidence threshold for corrections
- No original audio required
Smart Summarization
- Creates concise summaries of processed transcripts
- Supports multiple constraint types:
- Time-based (speaking duration)
- Character count
- Word count
- Preserves key information and context
- Maintains natural speaking rhythm
Project Structure
/
├── .gitignore # Git ignore file
├── LICENSE # MIT license file
├── README.md # This documentation
├── package.json # Package dependencies and scripts
├── tsconfig.json # TypeScript configuration
├── build/ # Compiled JavaScript files (generated after build)
│ ├── tools/ # Compiled tool implementations
│ └── utils/ # Compiled utility functions
└── src/ # Source TypeScript files
├── index.ts # MCP server entry point
├── tools/ # Tool implementations
│ ├── formatting.ts
│ ├── repair.ts
│ └── summary.ts
└── utils/ # Utility functions
├── file-handler.ts
└── logger.ts
Configuration
You can customize the server behavior by modifying the source code directly. The key configuration parameters are found in the respective tool implementation files:
// In src/tools/formatting.ts
const paragraph_gap = 8; // seconds
const line_gap = 4; // seconds
// In src/tools/repair.ts
const confidence_threshold = 90; // percentage
// In src/tools/summary.ts
const default_speaking_pace = 150; // words per minute
License
MIT
Verwandte Server
Agentic Tools
Provides AI assistants with advanced task management and memory capabilities using local JSON file storage.
mindpad
Save encrypted notes to your mindpad account
TaskMateAI
An AI-driven task management application controllable via MCP, supporting tasks, subtasks, priorities, and progress tracking.
Feishu MCP Server
Access and manage Feishu documents for AI coding tools, enabling structured content retrieval, editing, and search.
Rememberizer Common Knowledge
Access personal and team knowledge repositories, including documents and Slack discussions.
roampal-core
Persistent memory for Claude Code with outcome-based learning. Tracks what helped vs failed, auto-injects context via hooks.
OneNote
Access your entire OneNote knowledge base through AI using the Microsoft Graph API.
Bear MCP Server
Allows AI assistants to read notes from the Bear note-taking app by connecting directly to its SQLite database.
Garmin Workouts MCP
Create Garmin Connect workouts using natural language.
Obsidian via REST
Access and manage your Obsidian vault through a local REST API.