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

# Getting Started with MCPs

Connect your first MCP integration in 5 minutes.

## What are MCP Integrations?

MCP (Model Context Protocol) integrations allow your agents and workflows to connect to external tools and services without coding.

## Quick Start

### Step 1: Choose an Integration

Start with a popular tool:

* [Slack](https://github.com/PixelML/agenticflow-docs/blob/main/docs/07-integrations/mcp/all/slack.md) - Team notifications
* [Google Sheets](https://github.com/PixelML/agenticflow-docs/blob/main/docs/07-integrations/mcp/all/google-sheets.md) - Spreadsheet data
* [Gmail](https://github.com/PixelML/agenticflow-docs/blob/main/docs/07-integrations/mcp/all/gmail.md) - Email automation

### Step 2: Add to Agent or Workflow

**In Agents**:

1. Open agent configuration
2. Go to "Tools" tab
3. Search for integration name
4. Click "Add Tool"
5. Configure authentication

**In Workflows**:

1. Open workflow builder
2. Add integration node
3. Configure connection
4. Map inputs/outputs

### Step 3: Authenticate

Most integrations require authentication:

* **OAuth 2.0** (Recommended): Secure, no password sharing
* **API Key**: Simple key-based auth
* **Basic Auth**: Username/password

### Step 4: Test

Test your integration:

1. Send a test request
2. Verify connection
3. Check response data
4. Handle errors

## Common Use Cases

### Send Notifications

```
Workflow → Slack MCP → Post message to channel
```

### Retrieve Data

```
Agent → Google Sheets MCP → Read spreadsheet data → Response
```

### Create Records

```
Workflow → Salesforce MCP → Create lead → Email notification
```

## Next Steps

* [View All Integrations A-Z](https://github.com/PixelML/agenticflow-docs/blob/main/docs/07-integrations/mcp/all/README.md)

***

Need help? Check [Troubleshooting](/support/troubleshooting.md)


---

# 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 dynamically by asking a question.

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

```
GET https://docs.agenticflow.ai/integrations/getting-started.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.