> ## Documentation Index
> Fetch the complete documentation index at: https://docs.splox.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Tools

> The system tool packages, the MCP catalog, and how an agent gets one

**Tools** lists what your agents can reach for: the packages the platform runs
for everybody, and the MCP servers you connect yourself.

<Frame caption="Browse: the MCP catalog, with the transport and the kind of authentication on each card">
  <img src="https://mintcdn.com/sploxltd-165e0515/FtagtnY5r9E1DKmP/images/app/tools-catalog.png?fit=max&auto=format&n=FtagtnY5r9E1DKmP&q=85&s=b7e5b2fe8f35bc7f4120e48959464ff0" alt="The Tools catalog with Google Workspace, Linear, Notion and others" width="2880" height="1800" data-path="images/app/tools-catalog.png" />
</Frame>

Three tabs. **Browse** is the catalog of MCP servers you can connect, **System
tools** is what you already have, and **Your MCP servers** is what you have
connected so far.

## System tools

<Frame caption="The six system packages, each available in every run">
  <img src="https://mintcdn.com/sploxltd-165e0515/FtagtnY5r9E1DKmP/images/app/tools-system.png?fit=max&auto=format&n=FtagtnY5r9E1DKmP&q=85&s=fb633b67931ac9c0287fe42871775528" alt="The System tools tab listing Media, Search, Email, SMS, Memory and Harness" width="2880" height="1800" data-path="images/app/tools-system.png" />
</Frame>

Six packages, on for every agent on the account unless you turn one off:

| Package | What it is for                                                                    |
| ------- | --------------------------------------------------------------------------------- |
| Media   | Read images, audio, video and documents — binary in, text or structured data out. |
| Search  | Search the live web and pull page contents back as text.                          |
| Email   | An address of your own: read the mail sent to it, send mail from it.              |
| SMS     | A real phone number to receive SMS on, for a signup that asks for one.            |
| Memory  | Search everything said in past chats, and the window the run is carrying now.     |
| Harness | The questions about a harness that its own checkout cannot answer.                |

Each card says *Available in every run* and offers **Turn off**.

## What `system:` means

The slug on that screen is the second half of a name you write in code. An agent
gets a tool by naming its **source** in its declaration:

```python theme={null}
assistant = agent(
    "Assistant",
    system_prompt=prompt("assistant"),
    tools=[
        "system:compute",                          # a platform package
        "system:search#search",                    # one tool out of a package
        "tools/files.py",                          # a file of your own harness
        "019e4f9a-a679-79b4-a21c-7ff9c60b9181",    # an MCP server you connected
    ],
)
```

`system:<slug>` is a package the platform runs, credentials and all. You cannot
edit one and you do not publish anything for it to work. A `#` after the source
narrows it to named tools and nothing else.

<Note>
  `system:compute` — the runner every other tool executes through — is not on this
  screen, and neither is `system:splox`. They are sources you can name in code
  without being listed here as something to switch. The full list of sources your
  account can use comes back from
  [`/v2/tool-servers`](/api/tool-servers).
</Note>

So there are two switches, and they do different things. This screen decides what
your account **has**; the `tools` list in the harness decides what a given agent
**gets**. An agent is only ever offered what its own line names.
[Tools](/reference/tools) is the whole story, including writing your own.

## Connecting an MCP server

Pick a server from the catalog and Splox shows what connecting it takes. The
badges on the card said it already: `oauth` or `manual` for the credential,
`http` or `sse` for the transport.

<Frame caption="An OAuth server: you authorize at the provider, and Splox never sees the password">
  <img src="https://mintcdn.com/sploxltd-165e0515/FtagtnY5r9E1DKmP/images/app/tool-connect.png?fit=max&auto=format&n=FtagtnY5r9E1DKmP&q=85&s=91b7a6e6fd33ad60ba26d8763b982615" alt="The connect page for the Linear MCP server" width="2880" height="1800" data-path="images/app/tool-connect.png" />
</Frame>

* **OAuth** — name the connection and press Connect. You are sent to the
  provider to authorize, and back.
* **Manual** — the page asks for exactly the headers that server wants, named
  one by one (`X-api-key`, `X-access-token`, and so on), with a link to where you
  get them.

A server that is not in the catalog is **Add MCP server**:

<Frame caption="Adding a server the catalog does not have">
  <img src="https://mintcdn.com/sploxltd-165e0515/FtagtnY5r9E1DKmP/images/app/tool-custom.png?fit=max&auto=format&n=FtagtnY5r9E1DKmP&q=85&s=2b29297b5f42d7baa30aee86dec92a03" alt="The custom MCP server form with URL, transport and headers" width="2880" height="1800" data-path="images/app/tool-custom.png" />
</Frame>

Give it a name and a URL, pick the transport, and add whatever headers it
authenticates with. It then appears under **Your MCP servers** like any other,
and an agent gets it by putting its id in `tools`.

<CardGroup cols={2}>
  <Card title="Tools in the harness" icon="code" href="/reference/tools">
    Writing a tool of your own, and why tools are code and not JSON calls.
  </Card>

  <Card title="Tool servers over the API" icon="terminal" href="/api/tool-servers">
    Listing the sources and the tools inside them.
  </Card>
</CardGroup>