Arcanna

Provides MCP access to Arcanna AI use cases for resource management, code generation, job control, event queries, and feedback.

other

GitHub Stars

other

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "siscale-arcanna-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "ARCANNA_MANAGEMENT_API_KEY",
        "-e",
        "ARCANNA_HOST",
        "arcanna/arcanna-mcp-server"
      ],
      "env": {
        "ARCANNA_HOST": "<YOUR_ARCANNA_HOST_HERE>",
        "ARCANNA_MANAGEMENT_API_KEY": "<ARCANNA_MANAGEMENT_API_KEY>"
      }
    }
  }
}

The Arcanna MCP Server lets you interact with Arcanna’s AI use cases through the Model Context Protocol (MCP). It provides a programmable interface to manage resources, generate and run code, query events, and control Arcanna jobs and feedback loops from MCP clients.

How to use

You connect to the Arcanna MCP Server from your MCP client to perform operations such as creating and updating Arcanna resources, generating and executing code, managing jobs, and providing feedback to improve model accuracy. Use the MCP client to issue authorized requests for resource management, code generation and execution, event querying, and health checks. Start by ensuring your MCP client is configured to access the Arcanna MCP Server, then use the available tools to perform actions like upserting resources, generating code, starting or stopping jobs, and sending feedback.

How to install

Prerequisites you need before installing the MCP server include Docker installed on your machine. Follow the concrete steps to set up and run Arcanna MCP Server using the official Docker image or build the image locally.

Step-by-step commands:

# Prerequisite: install Docker
# Build the local image from the repository (optional)
docker build -t arcanna/arcanna-mcp-server . --progress=plain --no-cache

# Run the MCP server using the Docker image (example configuration)
docker run -i --rm \
  -e ARCANNA_MANAGEMENT_API_KEY=YOUR_API_KEY \
  -e ARCANNA_HOST=YOUR_ARCANNA_HOST \
  arcanna/arcanna-mcp-server

Configuration and usage notes

To enable MCP access, configure your MCP client to include the Arcanna MCP server entry in the mcpServers section. The example below shows how to wire the Docker-based runtime with the required environment variables.

Available tools

query_arcanna_events

Query events Arcanna has processed with support for multiple filters to refine results.

get_filter_fields

Helper tool to retrieve all possible fields that can be used to apply filters on Arcanna events.

upsert_resources

Create or update Arcanna resources such as jobs and integrations.

get_resources

Retrieve Arcanna resources, including jobs and integrations.

delete_resources

Delete Arcanna resources.

integration_parameters_schema

Helper tool to work with integration parameter schemas.

generate_code_agent

Generate code for Arcanna integrations or components.

execute_code

Execute the generated code and run the resulting blocks.

save_code

Save the generated code block as an Arcanna integration in the pipeline.

start_job

Begin event ingestion for a specified Arcanna job.

stop_job

Stop event ingestion for a specified Arcanna job.

train_job

Train the job’s AI model using provided feedback.

add_feedback_to_event

Submit feedback on AI decisions to improve model accuracy.

health_check

Check server health and Management API key validity.

Built by

VeilStrat

AI signals for GTM teams