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

# Quickstart

> Get up and running with AgentPass in minutes

This guide will walk you through setting up your first MCP server and tool in AgentPass Console. You'll be able to connect an AI agent to your MCP server in just a few steps.

> [!NOTE]
>
> We'll use OpenWeatherMap APIs as an example in this guide for ease of use. You can use your own APIs or services.

## Before you start

* Estimated time: 15 minutes
* If you don't have an AgentPass account, you can sign up [here](https://app.agentpass.ai).
* If you don't have an API key from OpenWeatherMap, you can sign up for a free account [here](https://home.openweathermap.org/users/sign_up). After signing up, you can get your API key from the [API Keys](https://home.openweathermap.org/api_keys) page.

## Step 1: Access the Console

**1. Login to AgentPass Console**

Navigate to [console](https://app.agentpass.ai) and sign in with your credentials.

## Step 2: Create Your First MCP Server

**1. Click Create Server**

From the Servers page, click the "Create Server" button to start the server creation process.

**2. Configure Server Details**

Fill in the basic server information:

* Name: `My First MCP Server`
* Description: `A server for testing MCP integration`

**3. Create the Server**

Click "Create Server" to finalize your MCP server setup.

## Step 3: Create Your First Tool

**1. Create New Tool**

Now you've landed on the [Flow Builder](https://www.agentpass.ai/docs/canvas/mcp-workflows.md). Here you can create your first tool.

* Click "Create your first tool"
* Choose "Create manually" for full control

**2. Configure Tool Basics**

Enter the tool information:

* **Name**: `get_weather`
* **Description**: `Get current weather for a location`
* **API URL**: `https://api.openweathermap.org/data/2.5/weather`
* **HTTP Method**: `GET`
* Click "Create Tool"

![Create new tool form showing basic configuration options](https://mintcdn.com/agentpass/CaVTOO8CIwxQ4npF/images/quickstart/quickstart-create-new-tool.jpeg?fit=max\&auto=format\&n=CaVTOO8CIwxQ4npF\&q=85\&s=edf654294ecf819e104bab429f35c62b)

**3. Define Parameters**

In the flow builder, you can see the tool you just created.

* Hover over the tool and click "Edit Tool" (pencil icon)
* Go to the Tab "Tool Parameters"

Add the following parameter:

* **Name**: `q`
* **Data type**: `string`
* **Description**: `Location`
* Click "Add Parameter" and then click "Save Changes"

![Tool parameter configuration](https://mintcdn.com/agentpass/CaVTOO8CIwxQ4npF/images/quickstart/quickstart-tool-parameters.jpeg?fit=max\&auto=format\&n=CaVTOO8CIwxQ4npF\&q=85\&s=29215c9833850d7546aaba104bb65828)

**4. Configure HTTP Request**

Move to the "HTTP Request" tab. This is where the API request will be configured.

Add a new parameter (Tab **Params**):

* **Name**: `appid`

* **Value**: `your-api-key` (remember to replace with your actual [API key](https://home.openweathermap.org/api_keys))

* Click "Save Changes"

![HTTP Request configuration](https://mintcdn.com/agentpass/CaVTOO8CIwxQ4npF/images/quickstart/quickstart-http-request.jpeg?fit=max\&auto=format\&n=CaVTOO8CIwxQ4npF\&q=85\&s=9e03d52e4d5d5d0094bec1b55719ce66)

## Step 4: Test Your Tool

**1. Access Tool Playground**

From the flow builder, hover your mcp tool and click the "Test" button to open the playground.

**2. Enter Test Parameters**

In the playground interface:

* Enter a test value for the `location` parameter (e.g., "London")

**3. Execute Test**

Click "Execute" to test your tool against the actual API.

**4. Review Results**

Examine the response to ensure your tool is working correctly:

* Check the HTTP status code
* Review the response data

![Tool test results](https://mintcdn.com/agentpass/CaVTOO8CIwxQ4npF/images/quickstart/quickstart-test-tool.jpeg?fit=max\&auto=format\&n=CaVTOO8CIwxQ4npF\&q=85\&s=2307949a567c71961c28049848c7f23b)

> [!TIP]
>
> Congratulations! You've successfully created and tested your first MCP tool.

## Bonus Step: Connect an AI Agent

**1. Choose Your AI Tool**

In the flow builder, in the AI Agent node,click "Connect"

**2. Follow Integration Guide**

Follow the specific integration guide for your chosen AI tool to add the MCP server connection.

**3. Test the Integration**

In your AI tool, try asking it to use your weather tool:

```
"Can you get the current weather for San Francisco?"
```

## Need Help?

* Visit our [concepts guide](https://www.agentpass.ai/docs/concepts.md) to understand MCP fundamentals
* Check out specific feature guides in the documentation sidebar
* Contact [support@agentpass.ai](mailto:support@agentpass.ai) for technical assistance

You're now ready to build more sophisticated MCP integrations with AgentPass Console!


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