by atlanhq
The Atlan Agent Toolkit enables AI agents to interact with the Atlan data catalog, facilitating AI-powered data discovery and automated data governance. It provides a Model Context Protocol (MCP) server that exposes Atlan's capabilities to Large Language Models (LLMs).
The Atlan Agent Toolkit is a collection of tools and protocols designed to enable AI agents to interact with Atlan, a modern data catalog and governance platform. The toolkit includes a Model Context Protocol (MCP) server that exposes Atlan's capabilities to Large Language Models (LLMs).
The primary component of the toolkit is the MCP server. To use it, you need to have an Atlan instance and the necessary credentials. The server can be run and connected to your MCP client, allowing you to use natural language to interact with your Atlan data catalog.
pyatlan
).Q: What is Atlan? A: Atlan is a collaborative data workspace that helps teams to discover, understand, and trust their data. It provides a unified view of all your data assets, along with rich context and collaboration features.
Q: What is the Model Context Protocol (MCP)? A: MCP is a protocol that allows Large Language Models (LLMs) to interact with external tools and services, enabling them to perform actions and access information beyond their built-in knowledge.
Q: Is the Atlan Agent Toolkit open source? A: Yes, the toolkit is open source and licensed under the MIT License.
This repository contains a collection of tools and protocols for interacting with Atlan services for AI agents. Each component is designed to provide specific functionality and can be used independently or together.
An MCP server that enables interaction with Atlan services through tool calling. Provides tools for asset search, and retrieval using pyatlan.
You can find the documentation and setup instructions for the MCP server here.
See CONTRIBUTING.md for details on how to contribute to the Atlan Agent Toolkit.
The project is licensed under the MIT License. Please see the LICENSE file for details.
Reviews feature coming soon
Stay tuned for community discussions and feedback