# AI Workspace Integration

Copy/paste the provided config block into your MCP configuration file:

{% stepper %}
{% step %}

#### Copy/Paste

Insert Eolas MCP servers into your AI app's MCP JSON config by pasting in the snippet

```
{
  "mcpServers": {
    "eolas-edge-mcp": {
      "command": "npx",
      "args": ["eolas-edge-mcp"]
    },
    "eolas-reach-mcp": {
      "command": "npx", 
      "args": ["eolas-reach-mcp"],
      "env": {
        "REPLICATE_API_TOKEN": "r8_...",  
        "CREATOR_BID_API_KEY": "your_creator_bid_api_key",
        "TELEGRAM_BOT_TOKEN": "your_telegram_bot_token"
      }
    }
  }
}
```

{% hint style="info" %}
Keys needed:

* Creator Bid (posting): `CREATOR_BID_API_KEY`
* Telegram bot: `TELEGRAM_BOT_TOKEN`
* Replicate (image/video tools): `REPLICATE_API_TOKEN`
  {% endhint %}
  {% endstep %}

{% step %}

#### Start

Open your app and ask the LLM to start EolasEdge. Use a prompt like: `Start EolasEdge` or `Load EolasEdge`.
{% endstep %}

{% step %}

#### Fund

{% hint style="info" %}
See examples such as Claude, Cursor, Gemini and other popular clients [here.](/eolas/getting-started/ai-workspace-integration/mcp-clients.md)
{% endhint %}

The LLM will return a unique wallet address. Fund it to enable on-chain trades. These funds are used directly by your AI for trading operations.
{% endstep %}
{% endstepper %}

{% hint style="warning" %}
Wallets are secured via your system’s [OS keychain](https://en.wikipedia.org/wiki/Keychain_\(software\)). No need to manage keys manually, but please take necessary precautions.
{% endhint %}


---

# Agent Instructions: Querying This Documentation

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

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://eolas.gitbook.io/eolas/getting-started/ai-workspace-integration.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.