> For the complete documentation index, see [llms.txt](https://docs.awenetwork.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.awenetwork.ai/infrastructure/overview/capability.md).

# Capability

**AWESOME helps agents discover and use tools, services and reusable skills.**

AI models can reason, but they need connections to external systems before they can retrieve data, call services and complete actions.

AWESOME provides that capability layer.

### AWESOME MCP

The [Model Context Protocol](https://modelcontextprotocol.io/docs/getting-started/intro) is an open standard for connecting AI applications to external data sources, tools and workflows.

The AWESOME MCP marketplace helps agents and builders:

* Discover MCP servers and available tools.
* Connect agents to APIs and external services.
* Reuse existing integrations instead of building each one from scratch.
* Combine multiple capabilities into agent workflows.

### Agent skills index

Agent skills package instructions and workflows for completing specific tasks.

AWE’s open skills index provides a shared place where builders can publish, discover and reuse these capabilities across agents.

MCP servers provide the tools an agent can access. Skills describe how an agent should use those tools to complete a task.

### Why capability matters

An agent’s usefulness depends on what it can reliably do.

A shared capability layer makes tools easier to discover, integrations more reusable and agents faster to build.

Within the AWE stack:

* **Identity** establishes which agent is acting.
* **Payments** allow it to pay and be paid.
* **Capability** determines what it can do.

[Open AWESOME →](https://mcp.awenetwork.ai/landing)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.awenetwork.ai/infrastructure/overview/capability.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
