> ## Documentation Index > Fetch the complete documentation index at: https://docs.xpander.ai/llms.txt > Use this file to discover all available pages before exploring further. # Desktop AI clients > Which clients run as harnesses inside xpander, which connect from a laptop, and what each connection carries. The same names play two roles. As a **harness**, the client runs inside xpander in a cloud session. As a **desktop client**, it runs on a laptop and reaches xpander over MCP. ![Diagram](https://docs.xpander.ai/images/diagrams/run-integrations-desktop-clients-307adb3e.svg) ## As harnesses inside xpander | Harness | Runs on xpander | Default when the organization's default provider is | | - | - | - | | Claude Code | Yes | Anthropic, or Amazon Bedrock with an Anthropic model | | Codex | Yes | OpenAI | | OpenCode | Yes | Any other provider the gateway routes | | Cursor | Not selectable yet | | Each conversation runs in its own sandbox with memory and CPU limits, gets the skills your organization made available and a short-lived [AI gateway](https://docs.xpander.ai/run/integrations/ai-gateway.md) token instead of a provider key, and is recorded on its task. The composer can switch harness or model, and the history carries over. ## As desktop clients Any MCP client (Claude Code, Claude Desktop, Cursor, ChatGPT or another) can connect to either endpoint. The client keeps its own model sign-in, including a personal Claude plan (Pro or Max) through `/login`. The MCP connection signs in to xpander separately and never touches the model sign-in. | Endpoint | What is behind it | Auth | | - | - | - | | `https://omni.xpander.ai/mcp` | Omni: task the organization's agents, build skills and agents from what admins approved, start cloud sessions, ask what a run did | OAuth 2.1 in the browser, per person | | `https://api.xpander.ai/mcp/` | The xpander API itself: agents, tasks and threads, skills and operations, custom functions, workspace files, schedules, usage. Not an agent. Each operation is one API call | OAuth 2.1, per person. No API key | ### Which endpoint to connect * **A person's own client: Omni.** One URL covers everything xpander Chat offers, and "Deploy this agent to xpander as a scheduled task" ends with an agent running in a cloud session. Setup: [Connect your MCP client](https://docs.xpander.ai/guides/deploy/omni-mcp.md). * **An integration or automation: the API endpoint.** Raw calls, with no agent deciding in between. Setup: [Model Context Protocol](https://docs.xpander.ai/api-reference/mcp.md). ### On a self-hosted install On Air-Gapped, the endpoint exists once `global.mcp.publicUrl` is set. Until then, the **MCP** row on **Platform > Agents > Channels** reads **Not offered on this install**. On Hybrid, the chart serves `mcp.` with nothing to set. If either page says the gateway is not available, contact [xpander support](https://xpander.ai/contact-us). A desktop client can also reach the organization's skills directly at the address on **Platform > Agents > Skills registry**, with each person signed in as themselves ([MCP gateway](https://docs.xpander.ai/run/integrations/mcp-gateway.md)). ## What is different between the two roles | On the laptop | In a cloud session | | - | - | | The client calls the vendor with its own sign-in (provider key or a personal plan such as Claude Pro or Max), unless pointed at the [LLM Gateway](https://docs.xpander.ai/run/llm-gateway/connect-tools.md) with an xpander key | The session holds a gateway token. The controller holds the key | | File edits, shell commands and local skills follow the client's own permission settings | Risky actions wait for a named person's approval | | Local history stays on the laptop. Only model calls sent through the LLM Gateway are recorded | Every task, skill call and answer is recorded | | Runs while the laptop is open | Runs unattended and answers in xpander Chat, Slack, Teams, email or on a schedule | ## Next steps > **[Connect a client to Omni](https://docs.xpander.ai/guides/deploy/omni-mcp.md)** > > Setup per client. > **[Connect a client to the API](https://docs.xpander.ai/api-reference/mcp.md)** > > The API over MCP. > **[Send laptop model calls through the gateway](https://docs.xpander.ai/run/llm-gateway/connect-tools.md)** > > Use an xpander key. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.