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
- Agent receives user request - “Send an email to john@example.com”
- Agent decides to use a tool - Determines SendGrid tool is needed
- MCP protocol bridges the connection - Standardized communication
- Connector executes the action - Actually sends the email via SendGrid API
- 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:- Agent analyzes user request - Understands what action is needed
- Agent selects appropriate tool - Chooses “send_email” from SendGrid connector
- Agent prepares parameters - Extracts to, subject, body from context
- MCP executes tool - Connector sends the email
- 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
- Checked before it is saved - A credential the vendor refuses never becomes a connection
- Connected once - The workspace holds it; each agent is then allowed to use it
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
MCP Protocol Flow
Authentication
Signing in (connectors and remote servers)
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
An agent that keeps the marketing site honest
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
Every service has its own, and they are the vendor’s to enforce: HubSpot allows 100 requests per 10 seconds, most AI providers meter by tokens or images, and a free tier is usually stricter than a paid one. When a vendor refuses a call, the agent is told in the vendor’s own words rather than being left to guess. BoostGPT counts calls too — every connector call is logged and charged against your plan’s allowance, whichever connector made it.Permissions
An agent can only use what you have connected and left switched on:How many connections
Each plan allows a number of connections, not connectors: two connections of the same service — a live Stripe and a test one — count as two. The Connectors screen shows where you stand against your plan in its header, and creating one past the limit is refused before anything is made.Next Steps
Quickstart
Connect your first service
Browse Connectors
See all available connectors
Build Custom
Create your own connector
Remote MCP servers
Connect a server the vendor runs