# Atlan for AI agents

> Part of Build and extend

Give your AI tools accurate, on-demand access to Atlan documentation—through Atlan docs over MCP for persistent connections or per-page Markdown export for one-time use.

- [Set up docs over MCP](https://docs.atlan.com/llms/platform/agents/set-up-docs-over-mcp/llms.txt): Connect Claude Code, Cursor, ChatGPT, or any MCP-compatible tool to Atlan docs over MCP for on-demand documentation access.
- [How to build context layer](https://docs.atlan.com/llms/platform/agents/build-a-context-layer/llms.txt): Build your first context layer for one domain, one team, and one AI client using Atlan connectors, context agents, and the Atlan MCP server.
- [How to build enterprise context layer](https://docs.atlan.com/llms/platform/agents/build-an-enterprise-context-layer/llms.txt): Build an enterprise context layer for AI agents across multiple domains, governed for compliance, using Atlan Context Studio and the Atlan MCP server.
- [How to set up memory layer for AI agents](https://docs.atlan.com/llms/platform/agents/set-up-a-memory-layer-for-ai-agents/llms.txt): Build long-term memory for AI agents with Atlan context repositories and the Atlan MCP server. Covers prerequisites, MCP wiring, and validation.
- [How to monitor your AI agents with Atlan](https://docs.atlan.com/llms/platform/agents/monitor-your-ai-agents-with-atlan/llms.txt): Add data-side observability to production AI agents with Atlan, covering lineage, access enforcement, and audit logs. Pair with an LLM observability tool.
- [How to write AGENTS.md file](https://docs.atlan.com/llms/platform/agents/write-an-agents-md-file/llms.txt): Write an AGENTS.md file for AI coding agents (Codex, Cursor, Copilot, Aider, Windsurf, Zed). Spec, examples, required and optional sections, and pitfalls.
- [Context layer](https://docs.atlan.com/llms/platform/agents/concepts-context-layer/llms.txt): Atlan provides a context layer, the governed layer that connects AI agents to trusted data.
- [Memory layer for AI agents](https://docs.atlan.com/llms/platform/agents/memory-layer/llms.txt): Understand how a memory layer maps to Atlan's architecture, and how context repositories and the Atlan MCP server compare to vector databases and RAG.
- [AI agent observability](https://docs.atlan.com/llms/platform/agents/ai-agent-observability/llms.txt): Understand why monitoring production AI agents requires two complementary layers, and how Atlan's data-side observability complements LLM observability tools.
- [AGENTS.md](https://docs.atlan.com/llms/platform/agents/concepts-agents-md/llms.txt): Understand what AGENTS.md is, which AI coding agents support it, and why keeping it short produces better agent outcomes than exhaustive files.
- [AI-ready data](https://docs.atlan.com/llms/platform/agents/concepts-ai-ready-data/llms.txt): AI-ready data is data that an AI agent can use reliably without the contextual inference a human analyst supplies. Understand how it differs from BI-ready data and what the distinction means for your metadata layer.
- [Docs-over-MCP tools](https://docs.atlan.com/llms/platform/agents/docs-over-mcp-tools/llms.txt): Reference for all seven tools exposed by Atlan docs over MCP: what each tool does, its inputs, and when to use it.
- [Context layer](https://docs.atlan.com/llms/platform/agents/faq-context-layer/llms.txt): Common questions about Atlan's context layer—enterprise rollouts, memory layers, and how Atlan compares to RAG, semantic layers, and vector databases.
- [AI agent monitoring](https://docs.atlan.com/llms/platform/agents/ai-agent-monitoring/llms.txt): Common questions about monitoring AI agents with Atlan, including how it compares to LLM observability tools and what data Atlan can surface.
- [AGENTS.md](https://docs.atlan.com/llms/platform/agents/faq-agents-md/llms.txt): Common questions about the AGENTS.md standard, placement, length, and how it compares to CLAUDE.md.
- [AI-ready data](https://docs.atlan.com/llms/platform/agents/faq-ai-ready-data/llms.txt): Common questions about AI-ready data—what it means, how to assess it, how it differs from BI-ready data, and how it connects to a context layer.