mcp-haystack
mcp-haystack is a Python library designed for data processing and analysis. It specializes in data searching and filtering, enabling efficient data manipulation. Users can easily operate on datasets and quickly retrieve necessary information, making it highly beneficial for data science and machine learning projects.
GitHub Stars
3
User Rating
Not Rated
Favorites
0
Views
45
Forks
0
Issues
0
MCP Haystack Integration
This repository provides an integration between Haystack and the Model Context Protocol (MCP). MCP is an open protocol that standardizes how applications provide context to LLMs, similar to how USB-C provides a standardized way to connect devices.
Overview
The MCP Haystack integration allows you to use MCP-compatible tools within Haystack pipelines. This enables your LLM applications to interact with external services and APIs through a standardized protocol, making it easier to build powerful, context-aware applications.
This integration includes a demo with the Rijksmuseum API, showcasing how to use MCP to search for artworks, get detailed information, and interact with the museum's collection.
Installation
Install from Source
git clone https://github.com/oryx1729/mcp-haystack.git
cd mcp-haystack
pip install -e .
Docker
This repository includes a Dockerfile that sets up a complete environment with an MCP Server Demo.
Building the Docker Image
docker build -t mcp-haystack-demo .
Running the Docker Container
docker run -p 8888:8888 mcp-haystack-demo
Rijksmuseum Demo
This repository includes a demo notebook that showcases how to use the MCP Haystack integration with the Rijksmuseum API. The demo allows you to:
- Search for artworks in the Rijksmuseum collection
- Get detailed information about specific artworks
- View artwork images
- Explore collections created by Rijksstudio users
- Get a chronological timeline of an artist's works
To run the demo:
- Obtain a Rijksmuseum API key from the Rijksmuseum website
- Run the Docker container or open the
examples/rijksmuseum_demo.ipynbnotebook