transcribeMCP
MCP server for GovTech's Transcribe speech-to-text service, enabling audio upload, batch transcription, summaries, minutes, sections, notes, and transcript Q&A.
README
transcribeMCP
MCP server for GovTech's Transcribe speech-to-text service. Lets an MCP client (Claude Code, Claude Desktop, etc.) upload audio, run batch transcriptions, and work with the results — summaries, minutes, sections, notes, and transcript Q&A chats.
Setup
- Get a Transcribe API key: log into https://www.transcribe.gov.sg/ and visit https://www.transcribe.gov.sg/dev_api_key (or use the
POST /auth/otps+POST /auth/tokens+POST /auth/apikeysflow if your org isn't on WOG-AD). API keys are valid for 90 days. - Install the package:
pip install -e . - Set the required environment variables:
TRANSCRIBE_API_KEY— your 90-day API keyTRANSCRIBE_EMAIL— the email address the API key was issued toTRANSCRIBE_BASE_URL— optional, defaults tohttps://core.transcribe.gov.sgTRANSCRIBE_API_VERSION— optional, defaults to3.0
Registering with Claude Code
claude mcp add transcribe \
--env TRANSCRIBE_API_KEY=your-api-key \
--env TRANSCRIBE_EMAIL=you@domain.gov.sg \
-- transcribemcp
Or add directly to .mcp.json:
{
"mcpServers": {
"transcribe": {
"command": "transcribemcp",
"env": {
"TRANSCRIBE_API_KEY": "your-api-key",
"TRANSCRIBE_EMAIL": "you@domain.gov.sg"
}
}
}
}
Registering with Claude Desktop
Add to your Claude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"transcribe": {
"command": "transcribemcp",
"env": {
"TRANSCRIBE_API_KEY": "your-api-key",
"TRANSCRIBE_EMAIL": "you@domain.gov.sg"
}
}
}
}
Scope
Covers batch transcription (workspaces, projects, transcriptions), summaries, minutes, sections, notes, and chat-based Q&A over a transcript. Live Transcription is not supported — it requires real-time WebRTC audio streaming, which doesn't fit an MCP tool-call model. See docs/superpowers/specs/2026-07-05-transcribe-mcp-server-design.md for the full design rationale.
Development
pip install -e ".[dev]"
pytest
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.