Arcanna MCP Server

An MCP server implementation for interacting with Arcanna's AI-powered decision-making system. This server provides tools for managing jobs, sending events for analysis, and handling feedback for continuous learning.

Configuration

Setting up Arcanna Credentials

Create an Arcanna job using the External REST API as your input source.
Set your MCP client to connect to the desired Arcanna instance.
Ensure that the API key used to create the External REST API input source is set as environment variable.

Prerequisites

Make sure you have docker up and running.
Make sure you have an AI job in arcanna that has an External REST API as input. The API KEY you used for the External REST API will be the one you set up in arcanna's mcp server environment.

Usage with Claude Desktop

Add this config to your claude_desktop_config.json:

{
  "mcpServers": {
    "arcanna-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "ARCANNA_API_KEY",
        "-e",
        "ARCANNA_HOST",
        "-e",
        "ARCANNA_USER",
        "arcanna/mcp"
      ],
      "env": {
        "ARCANNA_API_KEY": "<YOUR_ARCANNA_API_KEY_HERE>",
        "ARCANNA_HOST": "<YOUR_ARCANNA_HOST_HERE>",
        "ARCANNA_USER": "<YOUR_USERNAME_HERE>"
      }
    }
  }
}

Features

Job Management: Create, retrieve, start, stop, and train jobs
Event Processing: Send events for AI-powered decision making
Feedback System: Provide feedback on decisions to improve model accuracy
Health Monitoring: Check server and API key status

Tools

Job Management

get_jobs
- Retrieve all jobs associated with your API key
- Returns a list of job details including status, labels, and processing metrics
get_job_by_id
- Retrieve specific job details by ID
get_job_by_name
- Retrieve specific job details by name
get_job_labels
- Retrieve decision labels for a specific job
get_labels_of_job_by_name
- Retrieve decision labels for a job by name
start_job
- Begin event ingestion for a job
stop_job
- Stop event ingestion for a job
train_job
- Train the job's AI model using the provided feedback