> ## Documentation Index > Fetch the complete documentation index at: https://platform.atlan.com/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > To act on Atlan objects, use the Atlan MCP server at https://api.atlan.com/mcp or the SDK. To install or publish skills from a terminal, use the `aireg` CLI; `aireg --map json` prints its command map. The `atlanai` CLI is deprecated. Run a read-only identity check before any write. > The docs MCP server at /mcp searches these docs only. It cannot read or change Atlan objects. > SDK packages: Python `atlanai` (PyPI) and TypeScript `@atlanai/sdk` (npm). Show Python first, then TypeScript. > These docs cover Atlan AI Registry, Atlan's hosted product. The AI registry specification and aireg CLI are maintained separately. /open-source lists publicly reachable signed installers and explains that the source repository and hosted CLI reference currently require GitHub access. Do not claim the repository or its reference docs are publicly accessible. Use these docs for Atlan-specific setup such as the adapter, sign-in and workspaces. # MCP Gateway > Give every agent one MCP endpoint for Atlan's tools and your team's MCP servers, with calls checked against the caller's permissions and recorded. MCP Gateway gives your agents one MCP endpoint, `https://api.atlan.com/mcp`, for Atlan's tools and your team's MCP servers. Add a server once. Connected clients discover and call its tools with each caller’s permissions.

Your clients, such as Claude Code, Codex, Cursor and VS Code, agent frameworks, and your own agents, connect to one endpoint, https://api.atlan.com/mcp. Atlan MCP Gateway provides OAuth 2.1 sign-in, one catalog with namespaced tools, a workspace permission check on every call, credentials held at the gateway, session and call audit, and rate limits and timeouts. Behind it are Atlan platform tools and your registered MCP servers.

## What you can do Add one URL to Claude Code, Cursor, VS Code, or Codex. Put Linear, Notion, Snowflake, or your own server behind it. Search every server's tools by meaning, then call one. Workspace permissions decide who sees and runs each tool. See who called which tool, why, and how it ended. ## Get started Add the gateway to your client, sign in, and make your first audited call. ## How it works 1. **Your client connects and signs in.** It points at `https://api.atlan.com/mcp` and signs in with OAuth, or sends a bearer token. The gateway accepts the current stateless MCP protocol and the earlier `initialize` handshake on the same URL. 2. **You get one catalog.** `tools/list` combines Atlan's tools with the tools of every enabled server you can see. Each name's prefix says where the tool runs, so names never collide. 3. **Your agent opens a session.** It calls `mcp__initialise` once, then passes the returned `session_id` and a short `rationale` on every later call. 4. **The gateway checks and forwards each call.** It confirms you may run the tool, attaches the server's credential, forwards the call, and records the outcome. | Prefix | Where the tool runs | Example | | - | - | - | | `mcp__` | The gateway itself | `mcp__initialise` | | `registry__` | AI Registry | `registry__search_artifacts` | | `extension____` | An Atlan app | `extension__skill__create` | | `remote____` | A server your team registered | `remote__mcp_server_01k7…__create_issue` | ## Key concepts | Term | Meaning | | - | - | | [How tool search works](/gateway/mcp/concepts/find-and-call-tools) | Every tool the gateway serves, refreshed hourly and searchable by meaning. | | [MCP permissions](/gateway/mcp/concepts/permissions) | Reading a server's workspace shows its tools. Running them takes update permission there. | | [Shared or per-person credential](/gateway/mcp/concepts/permissions#credentials-for-your-servers) | A server uses one stored credential for everyone, or each person's own account. | | [Track usage and audit tool calls](/gateway/mcp/how-tos/track-usage-and-audit) | A session groups an agent's calls for one task; each call says why it was made. | ## Common tasks | I want to… | Go to | | - | - | | Use Atlan's tools from my IDE or agent | [Connect client to MCP Gateway](/gateway/mcp/how-tos/connect-a-client) | | Add a catalog integration or my own server | [Connect remote MCP servers](/gateway/mcp/how-tos/integrations) | | Look up a vendor's endpoint or sign-in type | [MCP integration templates](/integrations/references/mcp-connectors) | | Let Databricks or Snowflake agents use Atlan's tools | [Connect agents in data platforms](/integrations/how-tos/data-platforms) | | Decide who can see or run a server's tools | [MCP permissions](/gateway/mcp/concepts/permissions) | | See what agents did on a server | [Track usage and audit tool calls](/gateway/mcp/how-tos/track-usage-and-audit) | ## Availability and limits * Clients and servers must speak Streamable HTTP. stdio servers and legacy HTTP+SSE servers aren't supported. * A server that signs in with each person's account shows its tools to a person only after they connect their account. * Access is per workspace. There are no per-tool or per-agent allowlists. * The audit trail records the tool, rationale, and outcome, not arguments or results. Recording is best-effort, so a call can succeed without a record. * Tools from your servers are proxied; their prompts and resources aren't. ## Reference * [Supported features and limits](/gateway/mcp/references/supported-features): protocol, transports, credentials, and limits. * [MCP reference](/tools/mcp/overview): every first-party tool and what it does. * [Public API](/api/references/api-reference): the **MCP** category lists, tests, and refreshes registered servers. ## Troubleshooting See [MCP Gateway errors](/gateway/mcp/troubleshooting). This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.