# What are MCPs?

## What is MCP?

**MCP (Model Context Protocol)** is a standard protocol that allows AI agents and workflows to connect to external tools and services.

## Benefits

✅ **No-Code**: Connect tools without programming ✅ **Secure**: OAuth and encrypted credentials ✅ **Extensive**: 2,673+ integrations available ✅ **Flexible**: Use in agents, workflows, and workforce ✅ **Reliable**: Built-in error handling and retries

## How MCPs Work

### In Agents

1. Add tools to agent configuration
2. Agent can call tools during conversations
3. Results returned to agent automatically
4. Agent uses data to respond intelligently

### In Workflows

1. Add integration nodes to workflow
2. Configure authentication
3. Map inputs and outputs
4. Execute as part of automation

### In Workforce

1. Assign tools to specific team agents
2. Agents use tools as needed
3. Share results across team
4. Coordinate tool usage

## Integration Types

### Pre-built MCPs (2,673)

Ready-to-use integrations for popular services:

* Communication (Slack, Email, Teams)
* Data (Google Drive, Sheets, Databases)
* CRM (Salesforce, HubSpot)
* Development (GitHub, Jira)
* And 2,600+ more

### Custom Integrations

Build your own:

* [REST API Connections](https://github.com/PixelML/agenticflow-docs/blob/main/docs/07-integrations/mcp/custom-integrations/api-connections.md)
* [Webhooks](https://github.com/PixelML/agenticflow-docs/blob/main/docs/07-integrations/mcp/custom-integrations/webhooks.md)
* [OAuth Apps](https://github.com/PixelML/agenticflow-docs/blob/main/docs/07-integrations/mcp/custom-integrations/oauth-setup.md)

## Authentication

### OAuth 2.0 (Recommended)

* Most secure method
* No password sharing
* Granular permissions
* Automatic token refresh

### API Keys

* Simple setup
* Copy/paste key
* Stored encrypted
* Good for internal tools

### Basic Auth

* Username/password
* For legacy systems
* Encrypted storage

## Popular Categories

* [Communication](https://github.com/PixelML/agenticflow-docs/blob/main/docs/07-integrations/mcp/by-category/communication/README.md) - Chat, email, video
* [Data Storage](https://github.com/PixelML/agenticflow-docs/blob/main/docs/07-integrations/mcp/by-category/data-storage/README.md) - Files, databases
* [CRM & Sales](https://github.com/PixelML/agenticflow-docs/blob/main/docs/07-integrations/mcp/by-category/crm/README.md) - Customer management
* [Development](https://github.com/PixelML/agenticflow-docs/blob/main/docs/07-integrations/mcp/by-category/development/README.md) - Code, CI/CD
* [All Categories](https://github.com/PixelML/agenticflow-docs/blob/main/docs/07-integrations/mcp/by-category/README.md)

## Getting Started

1. [Connect Your First Integration](https://docs.agenticflow.ai/integrations/getting-started)
2. [Browse Popular Integrations](https://github.com/PixelML/agenticflow-docs/blob/main/docs/07-integrations/mcp/popular/README.md)
3. [Explore by Category](https://github.com/PixelML/agenticflow-docs/blob/main/docs/07-integrations/mcp/by-category/README.md)
4. [View Complete A-Z List](https://github.com/PixelML/agenticflow-docs/blob/main/docs/07-integrations/mcp/reference/README.md)

***

**Questions?** See [Integration FAQs](https://github.com/PixelML/agenticflow-docs/blob/main/docs/07-integrations/12-support/faqs.md#integrations)


---

# 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://docs.agenticflow.ai/integrations/overview.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.