MCPInstall
TransformerBee.mcp logo

TransformerBee.mcp

by Hochfrequenz 1 stars Hochfrequenz/TransformerBee.mcp

MCP server wrapper around transformer.bee aka edifact-bo4e-converter

READMEmain

TransformerBee.MCP

This is a simple PoC of a Model Context Protocol (MCP) server for transformer.bee, written in Python. Under the hood it uses python-mcp and transformerbeeclient.py.

Installation

You can install the MCP server as Python package or pull the Docker image.

Install as Python Package

uv install transformerbeemcp

or if you are using pip:

pip install transformerbeemcp

Install as Docker Image

docker pull ghcr.io/hochfrequenz/transformerbee.mcp:latest

Start the Server via CLI

Python

_The package ships a simple CLI argument to start the server. In a terminal inside the virtual environment in which you installed the package (here myvenv), call:

(myvenv) run-transformerbee-mcp-server

Docker

docker run --network host -i --rm -e TRANSFORMERBEE_HOST=http://localhost:5021 ghcr.io/hochfrequenz/transformerbee.mcp:latest

(For the environment variables -e ..., see below or the transformerbeeclient.py docs.)

Register MCP Server in Claude Desktop

If you checked out this repository

cd path/to/reporoot/src/transformerbeemcp
fastmcp install server.py

If you installed the package via pip/uv

Modify your claude_desktop_config.json (that can be found in Claude Desktop menu via "Datei > Einstellungen > Entwickler > Konfiguration bearbeiten"):

{
  "mcpServers": {
    "TransformerBee.mcp": {
      "command": "C:\\github\\MyProject\\.myvenv\\Scripts\\run-transformerbee-mcp-server.exe",
      "args": [],
      "env": {
        "TRANSFORMERBEE_HOST": "http://localhost:5021",
        "TRANSFORMERBEE_CLIENT_ID": "",
        "TRANSFORMERBEE_CLIENT_SECRET": ""
      }
    }
  }
}

where C:\github\MyProject\.myvenv is the path to your virtual environment where you installed the package and localhost:5021 exposes transformer.bee running in a docker container. Alternatively, if you haven't configured this handy CLI command https://github.com/Hochfrequenz/TransformerBee.mcp/blob/c0898769670469df13f23b57a55fe4b71ed9795b/pyproject.toml#L101-L102

you can just call python with non-empty args.

Note that a lot of MCP tooling assumes you have uv installed, so you might need to install it in your virtual environment as well.

For details about the environment variables and/or starting transformer.bee locally, check transformerbeeclient.py docs.

If you installed the package via Docker

{
  "mcpServers": {
    "TransformerBee.mcp": {
      "command": "docker",
      "args": [
        "run",
        "--network",
        "host",
        "-i",
        "--rm",
        "-e",
        "TRANSFORMERBEE_HOST=http://localhost:5021",
        "ghcr.io/hochfrequenz/transformerbee.mcp:latest"
      ],
      "env": {
        "TRANSFORMERBEE_HOST": "http://localhost:5021",
        "TRANSFORMERBEE_CLIENT_ID": "",
        "TRANSFORMERBEE_CLIENT_SECRET": ""
      }
    }
  }
}

I'm aware, that using the --network host option is a bit hacky and not best practice.

More Developer Tools MCP servers

Similar servers from the same category.

Sourcebot

sourcebot-dev

Enables code search across multiple repository hosts including GitHub, GitLab, Gitea, Gerrit, and Bitbucket with advanced filtering options for exploring large codebases through natural language queries.

searchgit

CodeAlive

codealive-ai

Provides a bridge to CodeAlive's platform for semantic code search, repository exploration, and context-aware chat completions that leverage deep understanding of entire codebases including documentation and dependencies.

search

Provides a secure, sandboxed environment for executing Python, Node.js, and shell commands in ephemeral containers with file management capabilities for code testing, visualization, and data analysis.

filesystemdatabase

NovaCV

lightbaby

Integrates with NovaCV API to generate, analyze, and convert resumes in various formats without dealing with complex document formatting

PDFSupport+5