Connectors

Connectors extend the capabilities of your AI assistants by enabling them to interact with external systems and data sources.

What are connectors?

Connectors are standardized interfaces that allow AI models to:

• Retrieve external data - Real-time information from various sources
• Execute actions - Perform tasks in connected systems
• Extend context - Relevant information for better responses
• Automate workflows - Orchestrate complex processes

Available connectors

Highlighted connectors

Microsoft 365

• Combines internal Microsoft 365 tools (Outlook, Calendar, Teams, SharePoint)
• Runs in user context with user-level permissions
• Best for email, meeting, chat, and document workflows

Google Workspace

• Unified Gmail and Calendar access in one connector
• Executes with the permissions of the authenticated user
• Best for inbox and scheduling workflows

Jira & Confluence

• Access Jira issues and Confluence knowledge
• Native mode runs in user context with user-level permissions
• Optional data-pool mode for large-scale knowledge search

All other connectors are listed under: All Connectors

Native connector vs. data pool

The same architecture pattern applies to Microsoft 365, Google Workspace, and Jira/Confluence:

• Native connector: executes in user context with user-level permissions
• Data pool (RAG): scalable retrieval on indexed datasets

Important: in data-pool setups, native user-level permissions from the source platform do not carry over automatically.

Database Tools

MCP Database

• Direct SQL queries
• Data analysis and manipulation
• Supports PostgreSQL, MySQL, SQLite
• Secure connection management

Documentation Tools

Context7

• Retrieve technical documentation
• API references
• Code examples
• Version-specific information

Built-in tools in Chats

Core built-in tools are now documented in the Chats section:

• Web Research
• Charts
• Code Sandbox
• Memory
• Calculator
• Excel

Business Tools

HubSpot

• Retrieve CRM data
• Manage contacts
• Deals and tickets
• Marketing automation

Stripe

• Retrieve payment data
• Transaction history
• Customer information
• Subscription management

Enabling connectors

In the Assistant Editor

1. Open the Assistant Editor
2. Navigate to the "Tools" section
3. Select desired connectors
4. Configure required parameters
5. Save the assistant

Tool Configuration

tools:
  - type: mcp
    name: database
    config:
      connection_string: ${DATABASE_URL}
      allowed_operations: ["SELECT"]
      
  - type: mcp
    name: web
    config:
      max_pages: 5
      timeout: 30

Custom MCP Servers

You can also integrate your own MCP servers:

Requirements

• Publicly accessible URL
• MCP protocol implementation
• HTTPS encryption
• Authentication (optional)

Integration

1. Add server URL in assistant
2. Configure authentication
3. Test available tools
4. Set permissions

Details: Custom MCP Server Integration

Security

Permission Model

• Tool-Level - Which tools can the assistant use?
• Operation-Level - Which actions are allowed?
• Data-Level - Which data can be accessed?
• User-Level - Who can use which tools?

Best Practices

1. Minimal permissions - Grant only necessary rights
2. Audit logging - Log all tool usage
3. Secure connections - Always use HTTPS/TLS
4. Secrets management - Store API keys securely
5. Rate limiting - Prevent abuse

Use Cases

Data Analysis

Assistant with Database + Charts Tools:
- Retrieve data from database
- Perform analysis
- Create visualization
- Present insights

Research Assistant

Assistant with Web Research + Context7 + Memory + Excel:
- Search web for information
- Retrieve technical documentation
- Save important findings
- Create summary

Business Intelligence

Assistant with HubSpot + Stripe + Database:
- Aggregate customer data
- Perform revenue analysis
- Identify trends
- Generate reports

Performance

Optimization

• Caching - Cache frequent requests
• Batching - Bundle multiple operations
• Timeouts - Set appropriate time limits
• Parallelization - Use independent tools in parallel

Monitoring

• Tool usage statistics
• Response times
• Error rates
• Cost monitoring

Troubleshooting

Common Issues

Tool not responding:

• Check connection
• Increase timeouts
• Analyze logs

Unexpected results:

• Verify tool configuration
• Validate permissions
• Check input format

Performance issues:

• Enable caching
• Optimize requests
• Use parallelization

Further Information

• Connector-specific Documentation
• Custom MCP Server Guide
• API Documentation
• Security Guidelines