Connector
A connector is a pre-built integration for a specific service (like Slack, GitHub, or Linear). Each connector includes:- Authentication setup (OAuth or API key)
- Available tools/operations
- Optimized responses for AI usage
Toolset
A toolset is a collection of connectors packaged together for your AI agent to use. You can combine multiple connectors into one toolset. Examples:- Single connector: Just Slack
- Multiple connectors: Slack + Linear + GitHub (for a triage workflow)
Tool
A tool is a specific operation within a connector. Tools are what your AI agent actually executes. Examples from Slack connector:post_message- Send a message to a channellist_channels- Get all channels in workspacecreate_channel- Create a new channel
MCP (Model Context Protocol)
MCP is the standard protocol that lets AI agents communicate with external tools. Think of it as the language AI agents use to call tools. Tadata handles all the MCP complexity for you - you don’t need to understand the protocol to use it.Agent
An agent is an AI system that can use tools to perform tasks. Examples include Claude Desktop, Cursor, or your custom AI implementation. Agents use MCP to discover available tools and execute them based on user requests.Common Terms
| Term | Definition |
|---|---|
| OAuth | Secure authentication method where you authorize Tadata to access a service on your behalf |
| Playground | Interactive environment in Tadata to test your toolsets before connecting to agents |
| Deployment | A specific version of your toolset configuration |
| Integration | Another term for connector - a connection to an external service |