Transkribus MCP Server
MCP server for the Transkribus REST API — manage collections, documents, HTR/OCR recognition, models, and more. 290 tools across 22 resource domains.
transkribus-mcp-server
MCP server for the Transkribus REST API. Manage collections, documents, HTR/OCR recognition, models, and more through the Model Context Protocol.
301 tools across 22 resource domains, with 8 entry points so you can pick the right server for your MCP client's tool limit.
Installation
npm install -g @lazyants/transkribus-mcp-server
Or run directly:
npx @lazyants/transkribus-mcp-server
Configuration
Transkribus uses session-based authentication. You can authenticate in two ways:
Option 1: Username + Password (auto-login)
export [email protected]
export TRANSKRIBUS_PASSWORD=your-password
The server will automatically log in and manage the session.
Option 2: Direct session ID
export TRANSKRIBUS_SESSION_ID=your-session-id
Use this if you already have a valid session from the Transkribus platform.
Entry Points
| Command | Domains | Tools |
|---|---|---|
transkribus-mcp-server | All 22 domains | 301 |
transkribus-mcp-collections | Auth, Collections (core/docs/pages/users/crowd/editdecl/credits/stats/labels/activity/tags) | 133 |
transkribus-mcp-admin | Auth, Admin, Credits, Uploads, Labels, Files, System, Root | 63 |
transkribus-mcp-transcription | Auth, Recognition, Layout Analysis, PyLaia, P2PaLA, DU | 48 |
transkribus-mcp-users | Auth, Users, Crowdsourcing, eLearning | 30 |
transkribus-mcp-models | Auth, Models | 27 |
transkribus-mcp-jobs | Auth, Jobs, Actions | 19 |
transkribus-mcp-search | Auth, Search, KWS | 17 |
Use split servers to reduce context size — pick only the splits you need.
Claude Code
Add to ~/.claude/settings.json:
{
"mcpServers": {
"transkribus": {
"command": "npx",
"args": ["-y", "@lazyants/transkribus-mcp-server"],
"env": {
"TRANSKRIBUS_USER": "[email protected]",
"TRANSKRIBUS_PASSWORD": "your-password"
}
}
}
}
Or use split servers (pick the splits you need):
{
"mcpServers": {
"transkribus-collections": {
"command": "npx",
"args": ["-y", "-p", "@lazyants/transkribus-mcp-server", "transkribus-mcp-collections"],
"env": {
"TRANSKRIBUS_USER": "[email protected]",
"TRANSKRIBUS_PASSWORD": "your-password"
}
},
"transkribus-transcription": {
"command": "npx",
"args": ["-y", "-p", "@lazyants/transkribus-mcp-server", "transkribus-mcp-transcription"],
"env": {
"TRANSKRIBUS_USER": "[email protected]",
"TRANSKRIBUS_PASSWORD": "your-password"
}
}
}
}
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"transkribus": {
"command": "npx",
"args": ["-y", "@lazyants/transkribus-mcp-server"],
"env": {
"TRANSKRIBUS_USER": "[email protected]",
"TRANSKRIBUS_PASSWORD": "your-password"
}
}
}
}
Security
- Never commit your credentials to version control
- Use environment variables or a
.envfile (excluded via.gitignore) - Session IDs expire — prefer username/password for long-running setups
Disclaimer
This is an unofficial MCP server for Transkribus. The authors are not affiliated with READ-COOP SCE. Use at your own risk.
License
MIT — see LICENSE for details.
เซิร์ฟเวอร์ที่เกี่ยวข้อง
Home Assistant
A free, private, and secure remote MCP server for Home Assistant.
Minesweeper MCP Server
An MCP server that allows client agents to play the game of Minesweeper.
Vigil
System Scanner for Vulnerabilities
LacyLights
AI-powered theatrical lighting design for the LacyLights system.
Plex MCP Server
Search for movies and manage playlists on your Plex Media Server using the Plex API.
aTars MCP by aarna
aTars MCP by aarna provides AI agents with structured access to crypto market signals, technical indicators, and sentiment analysis.
mcp-server-inject-bender
Security through absurdity: transforms SQL injection and XSS attempts into harmless comedy responses using AI-powered humor defense.
OpenRoute MCP
🗺️ MCP server to help plan routes using OpenRouteService.org, for activities such as hiking or mountain biking.
AI Endurance
AI coach for running, cycling, triathlon
Smart Home Device Control
Control smart home devices and query information by connecting large models to smart home backend APIs.