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
β No-Code: Connect tools without programming β Secure: OAuth and encrypted credentials β Extensive: 2,673+ integrations available β Flexible: Use in agents, workflows, and workforce β Reliable: Built-in error handling and retries
How MCPs Work
In Agents
Add tools to agent configuration
Agent can call tools during conversations
Results returned to agent automatically
Agent uses data to respond intelligently
In Workflows
Add integration nodes to workflow
Configure authentication
Map inputs and outputs
Execute as part of automation
In Workforce
Assign tools to specific team agents
Agents use tools as needed
Share results across team
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:
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 - Chat, email, video
Data Storage - Files, databases
CRM & Sales - Customer management
Development - Code, CI/CD
Getting Started
Questions? See Integration FAQs
Last updated
Was this helpful?