Skip to main content
Selecting Claude Code as a host runs the real Claude Code agent inside your project’s Computer (a cloud Linux sandbox) instead of MCPJam’s emulated chat loop. You are observing the actual runtime — its native tools, its own MCP client, its real execution behavior — not a simulation of it.
The Claude Code host is available to organizations where the feature has been enabled. Contact your account team if you don’t see it in the host template catalog.

​
What happens when you run a turn

  1. Pre-flight check. Before the stream opens, MCPJam verifies that the host can run: the model is an MCPJam-provided Anthropic model, the Computer data plane is configured, and the host settings are ones the runtime can honor. Any failure returns a clear error before the turn starts — a turn never silently falls back to the emulated engine.
  2. Computer wake. The host’s project Computer is reserved or woken (provisioned on first use). The Claude Code host requires a Computer — there is no local fallback.
  3. Credential delivery. MCPJam installs a short-lived model credential into the sandbox’s egress layer outside the VM. Neither the sandbox nor your browser ever holds a real model key. The agent runs pointed at MCPJam’s model proxy, which verifies the credential and meters every generation. There is no raw-key fallback.
  4. MCP delivery. Selected MCP servers are written into the session’s MCP config, each pointed at MCPJam’s per-server proxy tunnel — no upstream credentials enter the sandbox.
  5. The turn runs. Claude Code’s own agent loop executes; native tools (Bash, Read, Write, and others) run inside the sandbox; file changes land on the Computer’s disk; the transcript and trace persist like any other chat.

​
Host settings

Host-page tool-level toggles (such as tool visibility) are not re-enforced for Claude Code runs. Controls the runtime cannot honor are disabled in the UI rather than silently ignored.

​
Requirements

  • A project Computer (the E2B data plane must be configured for your deployment).
  • An MCPJam-provided Anthropic model selected on the host.
  • A signed-in project member — guest sessions cannot run the Claude Code host.
No credential configuration is needed. Broker delivery is on by default and the model proxy is always-on.

​
Billing

  • Computer time — the Claude Code runtime keeps the Computer awake, so it meters into your org’s monthly computer-time allowance exactly like terminal use.
  • Model tokens — every generation is priced and settled by the model proxy against your org, the same accounting as regular chat. Spend caps and empty-wallet rejections apply before the stream starts.

​
Failure modes

None of these fall back to the emulated engine — a turn that says it ran the real runtime did. All fail closed; a failed start spends nothing.
  • Computer — Manage your project’s Computer, sandbox images, and lifecycle.
  • Playground — The workspace where you select hosts and run turns.