> ## Documentation Index
> Fetch the complete documentation index at: https://mcpjam-mintlify-docs-update-pr-4053-1786992934526.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 and selected MCP servers (through a host-executed relay — see the caveat below).
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.** The two harnesses deliver MCP servers differently:
* **Claude Code (native)** — selected MCP servers are written into the session's MCP config, each pointed at MCPJam's per-server proxy tunnel. The runtime's own MCP client connects to them and the model calls the tools through native function calling. No upstream credentials enter the sandbox.
* **Codex (host-executed)** — the Codex CLI does not make MCP server tools model-callable in the mode MCPJam drives ([openai/codex#19425](https://github.com/openai/codex/issues/19425)), so MCPJam instead enumerates each selected server's tools at turn start and hands them to the agent as *host-executed* tools. The bridge injects their descriptions into the prompt, the model invokes them through a CLI shim, and **MCPJam executes them on its own server** against the already-authorized connection. Nothing about your servers — no URL, no token — enters the sandbox.
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 | Honored, via a host-executed relay rather than a native MCP client. Tools are named identically to Claude Code (`mcp____`), so traces and eval assertions match across the two harnesses. See the fidelity caveat below. |
| 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.
## Codex MCP fidelity caveat
Codex's MCP support is **not** equivalent to Claude Code's, and the difference matters if you are using it to benchmark a connector:
* The model does **not** call your tools through native function calling. The harness bridge injects each tool's name, description, and input schema into the prompt, and the model runs `node ''` through its built-in `bash` tool. Tool-selection behavior therefore reflects how well the model follows those shim instructions, not how a native MCP client would behave.
* Tools execute **host-side**, in MCPJam's server process, not in the sandbox. For a remote HTTP connector the difference is small (the same outbound request, from a different origin). For a stdio/local server it is larger — the server runs where MCPJam runs, not next to the agent.
* Tool schemas are enumerated **once, at turn start**. There is no `tools/list_changed` subscription, so a server that changes its tool list mid-turn is only picked up on the next turn.
* Every projected tool's description is part of the prompt, so a server with many tools inflates each turn of the conversation.
Claude Code hosts are unaffected by all of the above — they use the runtime's real MCP client.
## 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. |
| Require tool approval + selected MCP servers (Codex) | Pre-flight error — Codex runs the host's MCP tools on MCPJam's server and cannot pause them for approval. Turn approval off or remove the MCP servers. |
| 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. |
**Eval-specific pre-flight refusals** (harness eval runs only):
| Condition | What you see |
| ------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------- |
| Host grants `bash` but no computer environment is pinned on the suite | Pre-flight error — pin a computer environment in suite settings, or remove the computer-backed built-in from the host config. |
| Suite is scoped to the organization (no project) | Pre-flight error — the harness provisions and bills the computer against a project; move the suite into a project and retry. |
| A case pins a short model id (e.g. `claude-sonnet-4-6` instead of `anthropic/claude-sonnet-4-6`) | Pre-flight error naming both spellings — re-save the case with the full canonical id. |
## 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.