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

# Agent capabilities

> Choose between tools, MCP servers, skills, subagents, and outbound connections

Capabilities give an agent something beyond its instructions and model. Choose
the narrowest capability that fits the job.

| Capability        | Use it for                                             | Where the work happens                    | How it is attached                              |
| ----------------- | ------------------------------------------------------ | ----------------------------------------- | ----------------------------------------------- |
| Code-defined tool | One typed operation you implement                      | Your TypeScript `run()` function          | `useTool(tool)`                                 |
| MCP server        | A service that already publishes a collection of tools | The remote MCP server                     | `useMcpServer(server)`                          |
| Skill             | A reusable procedure, checklist, or supporting files   | The agent follows the loaded instructions | Place it under `skills/`                        |
| Subagent          | Delegating a focused task to another project agent     | The delegated agent                       | `useSubagent(agentId)`                          |
| HTTP connection   | A constrained authenticated outbound request           | OpenComputer sends the declared request   | Call `defineConnection().fetch()` inside a tool |

`useModel()` selects the model for a render, but it does not add an executable
capability.

## Tool or MCP server?

Use a [code-defined tool](/agents/tools) when you own the operation, want a
small schema, or need application-specific validation. Use an
[MCP server](/agents/mcp) when another service already hosts the tools.

Both ultimately give the model callable tools. A code-defined tool exposes the
single operation you register; an MCP server exposes the tools it advertises.

## Tool or skill?

A tool performs an operation and returns structured data. A
[skill](/agents/skills) teaches the agent how to approach a category of work.
Many agents use both: the skill describes the workflow while tools perform the
individual actions.

## Tool or subagent?

Use a tool for a bounded operation such as fetching an order. Use a
[subagent](/agents/subagents) when the task benefits from its own instructions,
model selection, capabilities, and working context.

## Connections are not managed accounts

`defineConnection()` declares a secret-backed HTTP destination. It is not an
OAuth account selector and does not itself give the model a tool. Call it from
a code-defined tool, or attach it to an MCP definition when that server accepts
the corresponding header-based authorization.

See [Secrets and outbound requests](/agents/secrets) for the complete security
model.