---
title: "Quickstart: MCP"
sidebar_label: MCP
description: "Give Claude Code the platform's benchmark tools with a scoped key, and run the first benchmark from a prompt."
---

Time to first result: about 10 minutes to a connected assistant, then 15 minutes for the run. [Using with AI (MCP)](../../mcp/index.md) is the full guide; this page is the short form.

1. **Create a key for the assistant.** **Settings**, then **Developer access**, **Create key**. Start from the **Worker** template, which is what [Using with AI (MCP)](../../mcp/index.md) and the **Connect an AI agent** box recommend: it carries the model, benchmark, cancel and serving-invoke permissions an assistant needs. Before you press Create, open **Advanced** and untick `hosted_devices:write`, `cloud_instances:write` and `cloud_credentials:write`, which spend money, and `orgs:write` unless the assistant should manage members: the template ticks them for an owner. Pick the project the key acts in with the dialog's **Project** field; every request the key makes acts there, whatever project the header shows later.
2. **Connect.** The same page's **Connect an AI agent** box prints this `claude mcp add` line with your platform's address filled in:

```bash
claude mcp add --transport http clika-rt-remote-full https://<platform>/api/mcp --header "Authorization: Bearer <key>"
```

   `/api/mcp` serves every tool your key can reach. The box's other line, `clika-rt-remote`, connects the narrower `benchmark-ops` toolset instead; `GET /api/mcp/toolsets` lists every toolset.

3. **Register the device.** Use the web dialog or the CLI's two commands ([Quickstart: CLI](cli.md)). An assistant can do it too when its key holds `devices:write`, which only an organization owner's or admin's key carries: on `device-ops` or `/api/mcp`, `post_enrollment_tokens` mints a token and `get_install` with it returns the one-line install command to run on the machine.
4. **Ask.** Once connected:

> Register HuggingFaceTB/SmolLM2-135M-Instruct, check which benchmark types it can run on my online Linux device, start a quick llm_performance run on it, poll once a minute until it finishes, and summarize tokens per second and time to first token.

   Start the first run a minute after the device enrolled; a run started earlier may be refused with `LICENSE_RECOVERY`. While it runs, `get_jobs_id` carries `run_progress` (cells done of the total for a performance run, items done for an accuracy run); the run takes about 15 minutes.

5. **What stays yours to do.** Issuing a runtime license, creating a key, and inviting or removing organization members are not tools; do them in the web application. A refusal says why: a tool outside the key's scope `requires the <capability> capability`, one that needs a signed-in session `takes a user session`, and `unknown tool` means no tool has that name.