Skip to content

OWL

Owl is the unified capability entry point provided by TrueWatch for tooling and intelligent scenarios, supporting two access forms: Owl CLI and Owl MCP Server.

Through Owl, users can uniformly invoke capabilities within TrueWatch such as Metrics, LOG, events, monitors, dashboards, APM, RUM, and infrastructure.

Owl does not replace the TrueWatch console or Open API. Instead, it provides encapsulated entry points on top of existing capabilities that are more suitable for tool invocation, automated orchestration, and use by AI Agents.

How It Works

flowchart LR
  user["User / Script"] --> cli["Owl CLI"]
  agent["AI Agent / MCP Client"] --> mcp["Owl MCP Server"]
  cli --> owl["Owl Tool Catalog & Execution Service"]
  mcp --> owl
  owl --> platform["TrueWatch Platform Capabilities"]

Owl CLI and Owl MCP Server access the same set of platform capabilities but are oriented towards different access methods and use cases.

Access Form Applicable Scenarios Core Capabilities
Owl CLI Local CLI, Scripts, and Automated Workflows Synchronize tool catalog, view tool descriptions, execute tools, export Agent Schema
Owl MCP Server AI Agent, MCP Client Integration Provide standardized tool service interfaces based on the Model Context Protocol

Use Cases

  • Query information such as Metrics, LOG, events, monitors, and dashboards in the terminal.
  • Quickly verify observability capabilities in a customer's workspace during implementation and delivery.
  • Integrate TrueWatch capabilities into AI clients that support MCP.
  • Enable Agents to invoke TrueWatch query, analysis, and management tools based on natural language.

Usage Limits

  • Owl's access permissions follow the API Key used. Resources that the API Key does not have permission to access cannot be accessed by Owl.
  • Write-type tools will modify resources within TrueWatch, such as creating dashboards, updating monitors, adding comments, etc.
  • When integrating with AI Agents or MCP clients, it is recommended to configure manual confirmation or approval mechanisms for write-type operations to avoid unintended changes.

Quick Start

Scenario 1: Command Line Operations

Suitable for developers, operations personnel, and implementation/delivery personnel to manually execute query and management tasks.

Scenario 2: AI Agent Integration

Suitable for integrating platform capabilities into large model applications to achieve natural language interaction.