Skip to main content
The Omni MCP endpoint puts Omni, the agent built into every organization, behind one URL. Connect it to Claude, ChatGPT, Cursor or any MCP client and work with Omni without leaving it.
From your client you can chat with Omni across turns, start long work and poll for it, and ask Omni to task your agents, build or edit agents, manage schedules and search your organization’s knowledge. You sign in once with OAuth 2.1, and every call runs with your permissions, where systems allow.
This is not the API’s MCP endpoint (api.xpander.ai/mcp/, also OAuth 2.1), which exposes the xpander API itself and is not an agent. The Omni endpoint is scoped to you: your conversations and your access.

Calls

Everything else (finding agents, building them, managing tasks, searching knowledge) you ask Omni for in plain words, plus the admin actions. Omni runs as you, so your own access bounds what a request can touch. For a direct connection to one agent, use the API’s MCP endpoint.

Continue a conversation

Pass the conversation_id back to ask_omni (or ask_omni_async) to continue the same thread.

Run long work without timing out

Runs can take minutes. If one may exceed your client’s timeout, start it with ask_omni_async and poll get_omni_task until it’s done.

Admin actions

Admins can read and change organization settings over the same endpoint. Each Platform area is one call that takes an action: They match the Omni sidekick admin actions. Your client lists only the calls your Platform role covers, and each is checked again when it runs. Secret values and new API key values never pass through. Applied changes go to the Audit log under your name. A connection with a bare API key has no person behind it, so admin calls refuse it.

Read and change settings

Reads answer at once. A change takes two calls:
  1. The first returns a preview (now and after) and a confirm_token. Nothing changes yet.
  2. Call again with that confirm_token and confirm set to true to apply it, or false to drop it.
The token works once, only for you and that call, and expires after about 10 minutes.

Authentication

OAuth 2.1 only, no API key. Most clients, including ChatGPT, Claude Code, Claude Desktop and Cursor, find the sign-in from the URL and open the browser. You sign in once and the client keeps the token.

Connect from a client

Add the endpoint once from the terminal, then sign in from inside a session:
In Claude Code, run /mcp, pick omni and complete the browser sign-in. From then on, ask in plain words: “Ask Omni what my agents did today” or “Deploy this agent to xpander as a scheduled task.” On a self-hosted install, replace the address with your installation’s MCP origin.

How Omni responds over MCP

MCP clients show plain Markdown, so Omni answers in self-contained Markdown and never raises an interactive card. If it needs something it can’t get here, such as a missing credential, it does what it can and tells you how to fix it in xpander Chat. If a skill needs authorization mid-run, ask_omni returns the link with the conversation_id. Authorize, then fetch the result with get_omni_task. These runs show in Session Manager tagged by client, for example “MCP - ChatGPT” or “MCP - Claude”.

Troubleshooting

The endpoint is OAuth-only and rejects x-api-key or any static key. Remove key-based config, re-add the endpoint and sign in in the browser.
Check the URL is exactly https://omni.xpander.ai/mcp and finish sign-in in the window the client opens. If a token is stale, remove and re-add the endpoint.
Open the link in Omni’s reply and authorize in xpander Chat. Then call get_omni_task with the same conversation_id.

Next steps

Call your agents over the MCP API

The API’s MCP endpoint.

Learn what Omni can do

Omni across xpander.