Skip to main content

What is MCP?

MCP (Model Context Protocol) is an open protocol that allows AI agents to connect to external tools and services. Think of it as a universal adapter that lets your agent interact with Slack, HubSpot, Calendly, and any other service.

How MCP Works

  1. Agent receives user request - “Send an email to john@example.com
  2. Agent decides to use a tool - Determines SendGrid tool is needed
  3. MCP protocol bridges the connection - Standardized communication
  4. Connector executes the action - Actually sends the email via SendGrid API
  5. Result returns to agent - “Email sent successfully”

Key Concepts

Connectors

Connectors are MCP-compatible servers that provide tools to your agent.

Tools

Tools are individual actions your agent can perform through a connector.

Tool Calling

When your agent needs to use a tool:
  1. Agent analyzes user request - Understands what action is needed
  2. Agent selects appropriate tool - Chooses “send_email” from SendGrid connector
  3. Agent prepares parameters - Extracts to, subject, body from context
  4. MCP executes tool - Connector sends the email
  5. Agent receives result - Uses response to continue conversation

Two Types of Connectors

1. Pre-built Connectors

BoostGPT provides 30+ ready-to-use connectors:
  • Managed by BoostGPT - We handle hosting, updates, and maintenance
  • OAuth authentication - Secure connection to your accounts
  • One-click deployment - Just authenticate and connect
Example: Deploying SendGrid

2. External MCP Servers

Connect any MCP-compatible server from the internet:
  • You provide the URL - Point to any MCP server
  • Third-party or self-hosted - Host your own or use community servers
  • Custom tools - Access specialized tools not in our library
Example: Connecting external server

MCP Protocol Flow

Authentication

OAuth Flow (Pre-built Connectors)

API Key (External Servers)

Security

Pre-built Connectors

  • OAuth 2.0 - Industry-standard secure authentication
  • Encrypted storage - Tokens encrypted at rest
  • Scoped permissions - Only request necessary permissions
  • Revokable access - Disconnect anytime from Dashboard

External Servers

  • HTTPS required - All MCP servers must use HTTPS
  • You control access - Manage authentication yourself
  • Audit logs - See all tool executions in agent Insights

Real-World Example

Building a Sales Agent

MCP vs Direct API Integration

Supported Tool Types

MCP connectors can provide various tool types:

Data Access

  • Read data (emails, contacts, files)
  • Search and filter
  • Query databases

Actions

  • Send messages
  • Create records
  • Update information
  • Delete items

Scheduled Tasks

  • Set reminders
  • Schedule events
  • Automate workflows

Real-time

  • Subscribe to events
  • Stream data
  • Webhooks

Building Your Own Connector

Want to create a custom MCP connector? See our guide:

Creating Connectors

Build your own MCP connector

MCP Protocol Spec

Technical protocol details

Debugging Tools

Agent Insights

View all tool executions:

Test in Playground

Limitations

Rate Limits

Each service has its own rate limits:
  • Gmail: 100 emails/day (free), 2,000/day (Google Workspace)
  • Salesforce: API limits by license tier
  • HubSpot: 100 requests/10 seconds
Your agent automatically respects these limits.

Permissions

Agents can only use tools you’ve connected:

Connector Availability

By plan:

Next Steps

Quickstart

Deploy your first connector

Browse Connectors

See all available connectors

Build Custom

Create your own connector

External Tools

Connect third-party servers