> ## Documentation Index
> Fetch the complete documentation index at: https://mcpjam-mintlify-docs-update-pr-3762-1786137034119.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# Claude Code and Codex hosts
> Run the real Claude Code or Codex agent inside your project's Computer — observe native tools, MCP client, and execution behavior directly
MCPJam supports two harness hosts that run a real agent runtime 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 agent loop, its real execution behavior — not a simulation of it.
* **Claude Code** — runs the real Claude Code agent with Anthropic models. Supports selected MCP servers and native tool approval.
* **Codex** — runs the real Codex CLI agent with OpenAI gpt-5 family models. Supports skills; does not support selected MCP servers.
The Claude Code and Codex hosts are available to organizations where the
respective feature has been enabled. Contact your account team if you don't
see them 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 supported by the selected harness, 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). Both harness hosts **require** 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.** For Claude Code hosts, 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. Codex hosts do not support selected MCP servers.
5. **The turn runs.** The agent's own loop executes; native tools run inside the sandbox; file changes land on the Computer's disk; the transcript and trace persist like any other chat.
## Host settings
### Claude Code
| Setting | Behavior |
| --------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Model | Honored — must be an MCPJam-provided Anthropic model. Bring-your-own-key models are not supported and fail closed. |
| System prompt | Honored — passed to the runtime. |
| Require tool approval | The toggle is disabled for Claude Code hosts. A host that already had approval enabled before switching to Claude Code will have approval honored for native tools: side-effecting built-ins (Bash, Write, etc.) pause the turn for your decision; read-only tools run freely. Approval cannot be combined with selected MCP servers — that combination is rejected at pre-flight. |
| Selected MCP servers | Honored — delivered via the session's MCP config through MCPJam's proxy. |
| Skills | Honored — runtime skills are materialized into the sandbox. |
| Temperature and other sampling controls | Not honored — the Claude Code runtime owns its own sampling. These controls are grayed out in the UI. |
| Progressive tool disclosure | Not applied — the real runtime owns tool discovery. |
### Codex
| Setting | Behavior |
| --------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------- |
| Model | Honored — must be an MCPJam-provided OpenAI gpt-5 family model. Other models are not supported and fail closed. |
| System prompt | Honored — passed to the runtime. |
| Require tool approval | Not supported — the Codex runtime does not pause for tool approval. The toggle is disabled. |
| Selected MCP servers | Not supported — Codex does not make MCP server tools model-callable. A Codex host with selected servers is rejected at pre-flight. |
| Skills | Honored — runtime skills are materialized into the sandbox. |
| Temperature and other sampling controls | Not honored — the Codex runtime owns its own sampling. These controls are grayed out in the UI. |
| Progressive tool disclosure | Not applied — the real runtime owns tool discovery. |
Host-page tool-level toggles (such as tool visibility) are not re-enforced
for harness 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).
* For **Claude Code**: an MCPJam-provided Anthropic model selected on the host.
* For **Codex**: an MCPJam-provided OpenAI gpt-5 family model selected on the host.
* A **signed-in project member** — guest sessions cannot run harness hosts.
No credential configuration is needed. Broker delivery is on by default and the model proxy is always-on.
## Billing
* **Computer time** — the harness 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.
| Condition | What you see |
| ---------------------------------------------------------- | ----------------------------------------------------------------------------- |
| Enterprise-managed authorization policy on the host | Pre-flight error — the combination is rejected rather than silently bypassed. |
| Require tool approval + selected MCP servers (Claude Code) | Pre-flight error — turn approval off or remove the MCP servers. |
| Selected MCP servers on a Codex host | Pre-flight error — Codex does not support MCP server tool delivery. |
| Computer data plane not configured | Pre-flight error naming the data plane requirement. |
| Model not supported by the selected harness | Pre-flight error asking you to pick an eligible model. |
| Computer at daily start cap | Start-limit dialog with upgrade option. |
| Org out of compute allowance and credits | Computer pauses with a billing notice. |
| Org spending limit reached | Clean rejection before any model call. |
| Sandbox dies mid-run | Turn errors; the next turn starts a fresh session. |
## Related
* [Computer](/inspector/computer) — Manage your project's Computer, sandbox images, and lifecycle.
* [Playground](/inspector/playground) — The workspace where you select hosts and run turns.