> ## Documentation Index
> Fetch the complete documentation index at: https://docs.air3.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Connect your agent

> Add the AIR docs MCP server to your agent, then start building.

## Connect via MCP

Choose your tool below and add the AIR documentation server:

```text theme={null}
https://docs.air3.com/mcp
```

<Tabs>
  <Tab title="Claude">
    <Steps>
      <Step title="Add the Moca Network MCP server to Claude">
        1. Navigate to the [Connectors](https://claude.ai/settings/connectors) page in the Claude settings.
        2. Select **Add custom connector**.
        3. Add the Moca Network MCP server:
           * Name: `MocaNetwork`
           * URL: `https://docs.air3.com/mcp`
        4. Select **Add**.
      </Step>

      <Step title="Access the MCP server in your chat">
        1. When using Claude, select the attachments button (the plus icon).
        2. Select the MocaNetwork MCP server.
        3. Ask Claude a question about Moca Network or AIR Kit.
      </Step>
    </Steps>

    See the [Model Context Protocol documentation](https://modelcontextprotocol.io/docs/tutorials/use-remote-mcp-server#connecting-to-a-remote-mcp-server) for more details.
  </Tab>

  <Tab title="Claude Code">
    <Steps>
      <Step title="Add the MCP server to Claude Code">
        Run the following command:

        ```bash theme={null}
        claude mcp add --transport http MocaNetwork https://docs.air3.com/mcp
        ```
      </Step>

      <Step title="Test the connection">
        Verify the connection by running:

        ```bash theme={null}
        claude mcp list
        ```
      </Step>
    </Steps>

    See the [Claude Code documentation](https://docs.anthropic.com/en/docs/claude-code/mcp#installing-mcp-servers) for more details.
  </Tab>

  <Tab title="Cursor">
    <Steps>
      <Step title="Open MCP settings">
        1. Use <kbd>Command</kbd> + <kbd>Shift</kbd> + <kbd>P</kbd> (<kbd>Ctrl</kbd> + <kbd>Shift</kbd> + <kbd>P</kbd> on Windows) to open the command palette.
        2. Search for "Open MCP settings".
        3. Select **Add custom MCP**. This opens the `mcp.json` file.
      </Step>

      <Step title="Configure the Moca Network MCP server">
        In `mcp.json`, add:

        ```json theme={null}
        {
          "mcpServers": {
            "MocaNetwork": {
              "url": "https://docs.air3.com/mcp"
            }
          }
        }
        ```
      </Step>

      <Step title="Test the connection">
        In Cursor's chat, ask "What tools do you have available?" Cursor should show the MocaNetwork MCP server as an available tool.
      </Step>
    </Steps>

    See the [Cursor documentation](https://docs.cursor.com/en/context/mcp#installing-mcp-servers) for more details.
  </Tab>

  <Tab title="VS Code">
    <Steps>
      <Step title="Create MCP configuration">
        Create a `.vscode/mcp.json` file in your project root.
      </Step>

      <Step title="Configure the Moca Network MCP server">
        In `.vscode/mcp.json`, add:

        ```json theme={null}
        {
          "servers": {
            "MocaNetwork": {
              "type": "http",
              "url": "https://docs.air3.com/mcp"
            }
          }
        }
        ```
      </Step>
    </Steps>

    See the [VS Code documentation](https://code.visualstudio.com/docs/copilot/chat/mcp-servers) for more details.
  </Tab>
</Tabs>

For another MCP-compatible tool, add the URL as a remote HTTP MCP server in its connection settings.

## Try your first prompt

Once connected, ask your agent to look up the docs and help with a specific task:

```text theme={null}
Use the AIR docs MCP server to help me add AIR Kit login to my app.
Check my framework and existing authentication, then explain the setup
and changes before implementing them.
```

You can also ask about credential issuance and verification, wallet transactions, or integration errors. Include your framework and what you have already built.

## Choose your setup

| Option | What it provides | When to use it |
| - | - | - |
| **Docs MCP** | Searchable AIR documentation, SDK guides, and API references. | Start here for current reference material. |
| **AIR skill** | Integration workflows and checks for setup, authentication, and common errors. | Add alongside MCP for guidance while building. |
| **Static docs** | Documentation files you attach or index in your tool. | Use when your tool cannot connect through MCP; refresh the files as docs change. |

Your agent uses these resources to plan, write, and review integration code. Live AIR operations run through your application's configured account, authentication, and programs.

## Add the AIR skill (optional)

For tools that support [Agent Skills](https://agentskills.io/home), run:

```bash theme={null}
npx skills add https://docs.air3.com
```

Select your agent in the CLI to install the skill.

<Accordion title="Before issuing or verifying credentials">
  Ask your agent to confirm these prerequisites before generating application code:

  * Your partner's public JWKS endpoint is reachable over HTTPS.
  * The exact JWKS URL is registered in the Developer Dashboard.
  * Your JWT signing key stays server-side, and its `kid` matches a published JWKS key.

  Follow [JWKS endpoint setup](/get-started/authentication/jwks-endpoint), then use the [issuance](/products/identity/issuing-credentials) or [verification](/products/identity/verify) guide for your flow.
</Accordion>

<Accordion title="Use static documentation files">
  ## Static docs files

  If your AI tool does not support MCP yet, you can use one of Moca Network's static documentation files instead.

  <Warning>
    Static files are snapshots and may not include the latest updates. Use MCP when possible for always-current docs.
  </Warning>

  ## Which file should I use?

  * **`llms.txt`** — A curated overview of Moca Network. Use it to route an agent to the right docs, understand product structure, and choose the right integration path.
  * **`llms-full.txt`** — A full static snapshot of the documentation. Use it when your tool needs more exhaustive reference material in one file.

  ## Setup with Cursor

  <Steps>
    <Step title="Open docs settings">
      Go to **Settings** → **Features** → **Docs**.
    </Step>

    <Step title="Add the overview file">
      Click **Add new doc** and paste: `https://docs.air3.com/llms.txt`
    </Step>

    <Step title="Optionally add the full snapshot">
      If your agent needs deeper static reference coverage, add: `https://docs.air3.com/llms-full.txt`
    </Step>

    <Step title="Reference in chat">
      Use **@docs** → **Moca** in your AI chat to reference the documentation.
    </Step>
  </Steps>

  ## Setup with Claude Desktop

  <Steps>
    <Step title="Download the overview file">
      Download the curated overview from: [https://docs.air3.com/llms.txt](https://docs.air3.com/llms.txt)
    </Step>

    <Step title="Optionally download the full snapshot">
      Download the full documentation snapshot from: [https://docs.air3.com/llms-full.txt](https://docs.air3.com/llms-full.txt)
    </Step>

    <Step title="Add to your project">
      Save one or both files in your project directory or another known location on your system.
    </Step>

    <Step title="Reference in chat">
      Drag and drop the file into your Claude Desktop chat, or use the attachment button to upload it. Claude will then have access to the uploaded Moca Network documentation context for that conversation.
    </Step>
  </Steps>
</Accordion>


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