MCP Server

Acteedog includes a built-in MCP (Model Context Protocol) server, allowing you to use Acteedog's features directly from any MCP-compatible AI agent such as Claude Desktop, Claude Code, or Cursor.

The MCP server starts automatically while Acteedog is running, at 127.0.0.1:61888/mcp.

Configuring Your AI Agent

Claude Desktop

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "acteedog": {
      "type": "http",
      "url": "http://localhost:61888/mcp"
    }
  }
}

Claude Code

Run the following command:

claude mcp add acteedog --transport http http://localhost:61888/mcp

Available Tools

Tool	Description
`list_connectors`	List all installed connectors
`trigger_activity_collection`	Trigger activity collection for a specified date
`get_job_status`	Check the status of an activity collection job
`get_activities`	Retrieve activity data for a specified date range
`save_daily_report`	Save a daily report in Markdown format

Example Workflow

By sending a request like the following to your AI agent, you can delegate the entire flow — from activity collection to report generation and saving:

Collect today's activities and generate and save a daily report.

Internally, the flow works as follows:

Confirm installed connectors with list_connectors
Trigger activity collection with trigger_activity_collection
Wait for the job to complete using get_job_status
Retrieve activity data with get_activities
LLM generates the daily report from the retrieved data
Save the generated report with save_daily_report

Next Steps

Install the Acteedog agent skills to automate your daily report workflow in Claude Code.

Skills

Install Acteedog agent skills for Claude Code and other AI assistants