transkribus-mcp-server
MCP server for the Transkribus REST API. Manage collections, documents, HTR/OCR recognition, models, and more through the Model Context Protocol.
README
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.
API scope: This server covers the legacy Transkribus TrpServer REST API. The newer Processing API v2 (OIDC auth,
/processing/v2,account.readcoop.eu) is intentionally out of scope.
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 TRANSKRIBUS_USER=your-email@example.com
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": "your-email@example.com",
"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": "your-email@example.com",
"TRANSKRIBUS_PASSWORD": "your-password"
}
},
"transkribus-transcription": {
"command": "npx",
"args": ["-y", "-p", "@lazyants/transkribus-mcp-server", "transkribus-mcp-transcription"],
"env": {
"TRANSKRIBUS_USER": "your-email@example.com",
"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": "your-email@example.com",
"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.
Releasing
Releases ship via the GitHub Release event. Maintainer flow:
- Bump the version in
package.jsonandserver.json(npm run check-versionsenforces alignment betweenpackage.json#/versionandserver.json#/packages[0].version). - Update
CHANGELOG.md. - Commit, then
gh release create vX.Y.Z --notes-from-tag(or write release notes inline). - The
Publish to npm + MCP Registryworkflow runs automatically: itnpm publishes with provenance, polls the registry until the tarball is available, then pushes the matchingserver.jsonto the MCP Registry viamcp-publisher.
The workflow skips npm publish cleanly if the version is already on npm (cutover guard for releases that were partially published manually).
npm authentication
Publishing uses npm Trusted Publishing: the workflow's GitHub OIDC token (id-token: write) is exchanged for a one-shot publish token at runtime. No NPM_TOKEN secret needs to live in the repo.
The binding is configured in the npm web UI (package → Trusted Publishers): provider GitHub Actions, organization lazyants, repository transkribus-mcp-server, workflow publish-registry.yml.
License
FSL-1.1-MIT — see LICENSE for the full terms. Versions 1.x remain MIT-licensed.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。