Tools Overview
Individual callable functions within toolkits that AI agents can discover and invoke.
What are Tools?
Tools are individual callable functions that live within toolkits. Each tool has a name, description, input schema, and is backed by a serverless function or HTTP endpoint. When an AI agent connects to an MCP server, it discovers the available tools and can call them to perform actions in the real world.
For example, a "Pushover Notifications" toolkit might contain a send-notification tool and a send-priority-alert tool, each with their own input schema and backing function.
Tool Properties
Every tool has the following properties:
| Property | Description |
|---|---|
| id | Unique identifier (UUID), auto-generated |
| toolkit_id | ID of the parent toolkit this tool belongs to |
| name | Unique string identifier for the tool (e.g., "send-notification") |
| display_name | Human-readable name shown in the UI |
| description | A brief description of what the tool does, sent to the AI agent for context |
| function_name | The serverless function or HTTP endpoint that backs this tool |
| input_schema | JSON Schema defining the tool's expected input parameters |
| requires_credentials | Whether the tool needs credentials to execute (boolean) |
| credential_provider_name | Name of the credential provider to use when resolving credentials |
| allowed_roles | Array of roles permitted to call this tool (for access control) |
| dangerous | Whether the tool performs destructive or irreversible actions (boolean) |
| timeout_seconds | Maximum execution time before the tool call is aborted |
| is_active | Whether the tool is currently enabled and available for use |
| usage_count | Total number of times the tool has been invoked |
How Tools Work
When an AI agent calls a tool via the MCP protocol (tools/call), Agent Dojo handles the full execution lifecycle:
Tool Resolution
Agent Dojo resolves the tool by name from the server's attached toolkits and validates the input against the tool's schema.
Credential Injection
If the tool requires credentials, Agent Dojo resolves them from the linked credential provider and injects them into the function call automatically.
Function Invocation
The backing serverless function is invoked with the validated arguments and resolved credentials.
MCP Response
The result is wrapped in the MCP response format and returned to the AI agent as a content array.
API Endpoints
Manage and invoke tools using the following API endpoints:
/mcp/toolsRegister a new tool within a toolkit
/mcp/tools/listList all available tools (MCP-compatible)
/mcp/tools/callCall a tool by name with arguments (MCP-compatible)