The TranscriptionTools MCP Server provides intelligent transcript processing capabilities including:
Repair transcription errors with over 90% confidence using repair_text
Retrieve detailed repair logs of previous operations with get_repair_log
Format timestamped transcripts into naturally readable text with format_transcript
Generate intelligent summaries using ACE cognitive methodology with various constraints (time, characters, words) via summary_text
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@TranscriptionTools MCP Server repair this transcript: 'We recieve about ten thousand dollars which is defiantly not enough.'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server providing intelligent transcript processing capabilities, featuring natural formatting, contextual repair, and smart summarization powered by Deep Thinking LLMs.
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
Related MCP server: Speak AI MCP Server
To install Transcription Tools for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @MushroomFleet/transcriptiontools-mcp --client claudeClone this repository:
git clone https://github.com/mushroomfleet/TranscriptionTools-MCP
cd TranscriptionTools-MCPInstall dependencies:
npm installBuild the server:
npm run buildConfigure the MCP server in your MCP settings file:
{
"mcpServers": {
"transcription-tools": {
"command": "node",
"args": ["/path/to/TranscriptionTools-MCP/build/index.js"],
"disabled": false,
"autoApprove": []
}
}
}<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><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><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><use_mcp_tool>
<server_name>transcription-tools</server_name>
<tool_name>get_repair_log</tool_name>
<arguments>
{
"session_id": "20241206143022"
}
</arguments>
</use_mcp_tool>Removes timestamps while preserving speech patterns
Applies intelligent spacing based on pause duration
Respects natural grammar and language flow
Maintains exact transcribed content
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
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
/
├── .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.tsYou 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 minuteMIT
TranscriptionTools-MCP — Transcript processing
DeepLucid3D-MCP — Cognitive processing
UNO-MCP — Narrative enhancement
gitea-mcp — Gitea integration
zero-vector-MCP — Procedural generation
Transforms timestamped transcripts into naturally formatted text
Inputs: input_text (required), is_file_path, line_gap, paragraph_gap.
Retrieves detailed analysis log from previous repair operation
Inputs: session_id (required).
Analyzes and repairs transcription errors with greater than 90% confidence
Inputs: input_text (required), is_file_path.
Generates intelligent summaries using ACE cognitive methodology
Inputs: input_text (required), constraint_type, constraint_value, is_file_path.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 4 tools
Each tool has a clearly distinct purpose: format_transcript transforms raw transcripts, repair_text fixes errors, summary_text creates summaries, and get_repair_log retrieves logs. There is no overlap in functionality, making tool selection unambiguous.
Three tools follow a consistent verb_noun pattern (format_transcript, repair_text, summary_text), but get_repair_log uses a verb_object pattern, deviating slightly. The naming is still highly readable and mostly predictable.
With 4 tools, the server is well-scoped for transcription processing. Each tool serves a distinct and essential function, and the count is appropriate for the domain without being too sparse or bloated.
The tools cover core transcription workflows: formatting, repairing, summarizing, and logging. Minor gaps might include operations like batch processing or exporting, but the set supports key agent tasks effectively.
Ask Claude about your meetings: summaries, action items and transcripts from Roomtone
Connect Claude to Fathom meeting recordings, transcripts, and summaries
Transcribe audio and video and work with your transcript library from any AI app. 119 languages.
Transcribe audio and video into speaker-labelled transcripts, subtitles, clips, and cited Q&A.
