> ## 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.

# Built-in tools

> Turn off the harness's or xpander's built-in tools so an agent acts only through what you attached.

An agent on Claude Code, Codex or OpenCode has two sets of built-in tools besides the skills you add:

* **Harness built-in tools**: the coding CLI's own shell, file read, write and edit, search, web fetch and search, sub-agents and plan mode.
* **xpander built-in tools**: what xpander gives every agent, such as memory, knowledge base search, web search, email, schedules, tasks to other agents, secrets, Slack, chat cards, screenshots, the browser, live surfaces, the services desk and `tell_user` progress updates.

Both are on by default. Turn one or both off when an agent must act only through what you attached, for example when it must not run shell commands or reach the web on its own. What you attached stays available either way.

## Set it in Agent settings

Open **Agent settings** from the gear in the conversation header, then **Advanced** > **Tools**:

Switch off **Harness built-in tools**, **xpander built-in tools**, or both. A note under the harness switch names what the agent still works through.

![Advanced pane of Agent settings with the Harness built-in tools and xpander built-in tools switches both on](https://mintcdn.com/xpanderai-099931d1/0KMvA3u0PK8VqjIR/images/use/built-in-tools-on.png?fit=max\&auto=format\&n=0KMvA3u0PK8VqjIR\&q=85\&s=1b3b82e7e08afdeba1afbd2136391c54)

Agent settings, Advanced, with both built-in tools switches on. Shown with sample data.

![Advanced pane of Agent settings with Harness built-in tools off, the note under it, and xpander built-in tools on](https://mintcdn.com/xpanderai-099931d1/0KMvA3u0PK8VqjIR/images/use/built-in-tools-harness-off.png?fit=max\&auto=format\&n=0KMvA3u0PK8VqjIR\&q=85\&s=a4e050a39588d1e4977a210f310cc9a6)

Harness built-in tools switched off: the note under it says what the agent still works through. Shown with sample data.

The switches show only on agents that run on a harness. A change applies to conversations started after it. See [Which value a turn uses](#which-value-a-turn-uses).

## What each switch removes

| Switch off | Removed | Still available |
| - | - | - |
| **Harness built-in tools** | The CLI's shell (`Bash`), file read, write and edit, search, web fetch and web search, sub-agents and plan mode. The agent's **Output format** keeps working. | xpander built-in tools (unless that switch is off too), and everything you attached |
| **xpander built-in tools** | Memory, knowledge base search, web search, email, schedules, tasks to other agents, secrets, Slack, chat cards, screenshots, the browser, live surfaces, the services desk, `tell_user` | Harness built-in tools (unless that switch is off too), and everything you attached |
| Both | Everything above | Skills (API and MCP connectors), custom functions, workflows and sub-agents you attached |

The agent's instructions follow the switches: with a set off, the agent is not told about what it no longer has.

### Codex and Harness built-in tools

With **Harness built-in tools** off, Codex keeps `request_user_input` and its read-only MCP resource helpers (`list_mcp_resources`, `list_mcp_resource_templates`, `read_mcp_resource`), which have no switch. The helpers only read from MCP connectors already attached to the agent, and nobody answers `request_user_input` during a run. Shell, file edits (`apply_patch`), web search, code mode and Codex sub-agents are removed. Claude Code and OpenCode keep none of their own built-in tools.

## Set it over the API

The agent setting is `harness_settings.builtin_tools`. Each half is `{"enabled": true}` or `{"enabled": false}`, and a missing half is on. Send it with [Update Agent](https://docs.xpander.ai/api-reference/v1/agents/update-agent.md) and `deploy=true` so it applies right away:

```bash theme={"dark"}
curl -X PATCH 'https://api.xpander.ai/v1/agents/<agent_id>?deploy=true' \
  -H "x-api-key: $XPANDER_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"harness_settings": {"builtin_tools": {"harness": {"enabled": false}, "xpander": {"enabled": false}}}}'
```

An update that names one half keeps the other as stored. An update to another harness setting keeps `builtin_tools` as it is. This turns xpander built-in tools back on and leaves the harness half alone:

```bash theme={"dark"}
curl -X PATCH 'https://api.xpander.ai/v1/agents/<agent_id>?deploy=true' \
  -H "x-api-key: $XPANDER_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"harness_settings": {"builtin_tools": {"xpander": {"enabled": true}}}}'
```

### Override for one call

The [invoke endpoints](https://docs.xpander.ai/use/agents/api.md#start-a-run) (`/invoke`, `/invoke/async` and `/invoke/stream`) take `builtin_tools` in the body with the same shape. It overrides the agent setting for that call, in either direction, and either half can be named alone. The agent setting does not change. This turns harness built-in tools on for one run of an agent whose setting has them off:

```bash theme={"dark"}
curl -X POST 'https://api.xpander.ai/v1/agents/<agent_id>/invoke/async' \
  -H "x-api-key: $XPANDER_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"input": {"text": "Run the test suite and summarize the failures"}, "builtin_tools": {"harness": {"enabled": true}}}'
```

On an agent that does not run on a harness, `builtin_tools` is ignored.

### See what a run used

`GET /v1/tasks/{task_id}` returns the value the run resolved, with both halves filled in:

```json theme={"dark"}
{"builtin_tools": {"harness": {"enabled": true}, "xpander": {"enabled": false}}}
```

## Which value a turn uses

Each half is resolved on its own, first match wins:

1. The call's `builtin_tools`.
2. The conversation's value.
3. The agent's `harness_settings.builtin_tools`.
4. On.

A conversation keeps the value resolved on its first message. A change to the agent setting applies to conversations started after it. A call that continues a conversation (with its `id`) and names a half changes that half for the conversation from then on. The half it does not name keeps the conversation's value.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.