EU AI Act Compliance Chatbot
About
An MCP server to answer questions on the original EU AI Act
Details
- Author
- thoughtgeek
- Downloads
- 172
- Categories
- AI
Jump to
- Hybrid retrieval using vector search and knowledge graph
- Processes EU AI Act PDF to populate vector store and graph
- Runs as a FastAPI application with interactive docs
- Deployable to AWS Lambda as a serverless function
- Includes tests via pytest
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
EU AI Act Compliance ChatbotCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install dependencies with Poetry, set up environment variables, download the EU AI Act PDF into a data/ directory, then run the processing script python -m scripts.process_eu_ai_act. Start the FastAPI API with uvicorn src.eu_ai_act_chatbot.api.main:app --reload. The interactive documentation is available at http://127.0.0.1:8000/docs.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"eu ai act compliance chatbot": {
"aicompliance_mcp": {
"command": "python",
"args": [
"-m",
"scripts.process_eu_ai_act"
]
}
}
}
}McpServers
{
"aicompliance_mcp": {
"command": "python",
"args": [
"-m",
"scripts.process_eu_ai_act"
]
}
}EU AI Act Compliance Chatbot
A chatbot designed to answer questions about the EU AI Act using a hybrid retrieval approach (vector search + knowledge graph).
Setup
1. Install Poetry: If you don't have Poetry installed, follow the instructions here.
2. Clone the repository:
git clone <your-repo-url>
cd eu-ai-act-chatbot
3. Install dependencies:
poetry install
4. Set up environment variables:
- Copy the
.env.example file to .env: cp .env .env # Or .env.example if you rename the template
- Fill in your API keys and service details in the
.env file.5. Download the EU AI Act PDF: Place the PDF file in a
data/ directory (you might need to create it) and name it eu_ai_act.pdf.
Processing Data
To process the EU AI Act document and populate the vector store and knowledge graph:
poetry shell
python -m scripts.process_eu_ai_act
Running the API
To run the FastAPI application locally:
poetry shell
uvicorn src.eu_ai_act_chatbot.api.main:app --reload
The API will be available at http://127.0.0.1:8000. You can access the interactive documentation at http://127.0.0.1:8000/docs.
Running Tests
poetry shell
pytest
Deployment (AWS Lambda)
1. Create a deployment package:
# Ensure dependencies are installed in the project's virtual env
poetry install --no-dev
# Create the package directory
mkdir package
# Install dependencies into the package directory
poetry run pip install --upgrade pip
poetry run pip install -r <(poetry export -f requirements.txt --without-hashes) --target ./package
# Copy source code and Lambda handler
cp -r ./src ./package/
cp lambda_function.py ./package/
# Create the zip file
cd package
zip -r ../deployment.zip .
cd ..
2. Upload
deployment.zip to your AWS Lambda function.3. Ensure the Lambda function's handler is set to
lambda_function.lambda_handler.4. Configure necessary environment variables in the Lambda function settings.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
