Atlan for AI agents

✦TL;DR

Use Atlan as the governed context and metadata layer behind your own AI agents and pipelines—build a context layer, set up agent memory, monitor agents, and write an AGENTS.md file.

||

Your AI can read this via Docs MCPcurl -fsSL "https://docs.atlan.com/install-docs-mcp" | bashConnect

Atlan is the governed context and metadata layer behind your AI agents. These how-tos cover common patterns for building, serving, and monitoring agent context with Atlan as the enabling layer.

Looking for Atlan MCP, or Atlan docs over MCP?

• Atlan MCP is the primary MCP server for the Atlan product—direct, live access to Atlan as a context layer for AI clients and automation platforms.
• Atlan docs over MCP gives your AI tool access to Atlan's own documentation, not your Atlan data.

This page covers a different layer: using Atlan as the governed context and metadata foundation for agents and pipelines you build yourself.

How-tos

• Build a context layer: your first single-domain build for one team and one AI client.
• Build an enterprise context layer: a multi-domain, governed, compliance-ready program.
• Set up a memory layer for AI agents: long-term, governed agent memory using context repositories and MCP.
• Monitor your AI agents with Atlan: data-side observability that pairs with your LLM observability tool.
• Write an AGENTS.md file: instruct AI coding agents and point them at Atlan context.

To have Atlan build that context for you rather than assembling it yourself, connect a knowledge source and create an agent from a template. See Understand agent templates.

Concepts

• Context layer
• Memory layer
• AI agent observability
• AGENTS.md
• AI-ready data

FAQ

• Context layer
• AI agent monitoring
• AGENTS.md
• AI-ready data

See also

• Atlan docs over MCP: connect your AI tool to Atlan's documentation.
• Atlan MCP overview