MCP Servers Overview
MCP (Model Context Protocol) servers extend your chatbot's capabilities by connecting to external tools and services.
What is MCP?
MCP is a standard protocol that allows AI models to:
- Access external data sources
- Execute actions in other systems
- Retrieve real-time information
- Perform calculations and operations
How It Works
graph LR
A[User Question] --> B[Chatbot]
B --> C{Needs External Data?}
C -->|Yes| D[MCP Server]
D --> E[External Service]
E --> D
D --> B
C -->|No| F[Knowledge Base]
F --> B
B --> G[Response]
- User asks a question
- Chatbot determines if external data is needed
- If yes, calls the appropriate MCP server
- Server retrieves/processes data
- Response is generated with the data
Available Integrations
Built-in Servers
Pre-configured integrations ready to use:
| Server | Description |
|---|---|
| Calculator | Mathematical operations |
| Weather | Current weather data |
| Salesforce | CRM data access |
| Atlassian | Jira/Confluence access |
| PostgreSQL | Database queries |
See Built-in Servers for details.
Custom Servers
Add your own MCP servers:
- HTTP-based servers
- stdio-based servers
- Custom implementations
See Custom Servers for details.
Enabling MCP Servers
- Open your chatbot
- Go to "Settings" > "Integrations"
- Find the MCP server
- Toggle "Enable"
- Configure any required settings
- Click "Save"
Authentication
Some MCP servers require authentication:
| Type | Description |
|---|---|
| OAuth | User authorizes access |
| API Key | Single key for all users |
| Centralized | Admin credentials for all |
See OAuth Configuration for details.
Use Cases
Customer Support
Connect to:
- CRM (Salesforce) for customer data
- Ticketing system for issue history
- Knowledge bases
Internal Tools
Connect to:
- Databases for live data
- Project management (Jira, Confluence)
- Internal APIs
Data Analysis
Connect to:
- PostgreSQL for database queries
- Calculator for computations
- External APIs for data
Best Practices
- Only enable servers you need
- Configure appropriate access controls
- Test thoroughly before deploying
- Monitor usage and performance
Security Considerations
- MCP servers can access external systems
- Review permissions carefully
- Use least-privilege access
- Audit integrations regularly