Alteryx Server

AYX-MCP-Wrapper

⚠️ DISCLAIMER

This is NOT an official implementation.

This project is a personal initiative and is not affiliated with, endorsed by, or supported by any company. Even if the maintainer is an employee of a related company, this project is developed independently without any official backing or support.

---

A Model Context Protocol (MCP) server that provides a comprehensive interface to Alteryx Servers. This wrapper enables AI assistants and other MCP clients to interact with Alteryx Server for managing workflows, collections, users, schedules, credentials, and more.

Features

• Advanced Search: Find users, workflows, and assets with flexible search options
• Workflow Operations: Execute, transfer, and manage workflows with full control
• Workflow Assets: Download workflow packages and extract XML for analysis
• Job Monitoring: Track and manage workflow execution jobs in real-time
• Collections Management: Create, update, delete, and organize collections
• User Management: Manage users, their assets, and permissions efficiently
• Schedule Management: Create and manage workflow schedules and automation
• Credential Management: Handle server credentials and secure connections

Prerequisites

• Python 3.10+ - Modern Python with type hints support
• Alteryx Server - With API access enabled
• OAuth2 Credentials - Client ID and Secret for authentication

Installation

Quick Start with uv (Recommended)

# Install uv if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh

# Install the MCP server
uv pip install mcp-server-alteryx

Using pip

pip install mcp-server-alteryx

From Source

git clone https://github.com/jupiterbak/AYX-MCP-Wrapper.git
cd AYX-MCP-Wrapper
uv sync
uv run pip install -e .

Configuration

Environment Variables

Set up your Server credentials using environment variables:

# Required: Server API URL
export ALTERYX_API_HOST="https://your-server.com/webapi/"

# Required: OAuth2 Client Credentials
export ALTERYX_CLIENT_ID="your-client-id"
export ALTERYX_CLIENT_SECRET="your-client-secret"

# Optional: SSL Verification (default: true)
export ALTERYX_VERIFY_SSL="1"

# Optional: temporary folder
export ALTERYX_TEMP_DIRECTORY="your-temp-directory"

# Optional: Logging level
export LOG_LEVEL="INFO"

Configuration File

Alternatively, create a .env file in your project root:

ALTERYX_API_HOST=https://your-server.com/webapi/
ALTERYX_CLIENT_ID=your-client-id
ALTERYX_CLIENT_SECRET=your-client-secret
ALTERYX_VERIFY_SSL=1
ALTERYX_TEMP_DIRECTORY=your-temp-directory
LOG_LEVEL=INFO

Usage

Claude Desktop Integration

To use this MCP server with Claude Desktop, add the following configuration to your Claude Desktop settings:

{
  "mcpServers": {
    "alteryx": {
      "command": "uvx",
      "args": ["mcp-server-alteryx", "--transport", "stdio"],
      "env": {
        "ALTERYX_API_HOST": "https://your-server.com/webapi/",
        "ALTERYX_CLIENT_ID": "your-client-id",
        "ALTERYX_CLIENT_SECRET": "your-client-secret",
        "ALTERYX_VERIFY_SSL": "1",
        "ALTERYX_TEMP_DIRECTORY": "your-temp-directory"
      }
    }
  }
}

However, we recommend to use it in combination with the "Sequential Thinking" tool:

```json
{   "mcpServers": {
  "sequential-thinking": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-sequential-thinking"
      ]
    },
    "alteryx": {
      "command": "uvx",
      "args": ["mcp-server-alteryx", "--transport", "stdio"],
      "env": {
        "ALTERYX_API_HOST": "http://localhost/webapi/",
        "ALTERYX_CLIENT_ID": "your-client-id",
        "ALTERYX_CLIENT_SECRET": "your-client-secret",
        "ALTERYX_VERIFY_SSL": "1",
        "ALTERYX_TEMP_DIRECTORY": "your-temp-directory"
      }
    }
  }
}

Configuration Options:

• command: The uvx executable to use
• args: Command line arguments for the MCP server
• env: Environment variables for Server authentication

Transport Options:

• stdio: Standard input/output (recommended for Claude Desktop)
• sse: Server-Sent Events
• streamable-http: HTTP streaming

Cursor Integration

For Cursor IDE integration, add to your Cursor settings:

{
  "mcpServers": {
    "alteryx": {
      "command": "uvx",
      "args": ["mcp-server-alteryx", "--transport", "stdio"],
      "env": {
        "ALTERYX_API_HOST": "https://your-alteryx-server.com/webapi/",
        "ALTERYX_CLIENT_ID": "your-client-id",
        "ALTERYX_CLIENT_SECRET": "your-client-secret",
        "ALTERYX_TEMP_DIRECTORY": "your-temp-directory"
      }
    }
  }
}

Command Line Interface

The MCP server can be run with different transport options:

# Using stdio transport (default)
uvx run src.main --transport stdio

# Using Server-Sent Events (SSE)
uvx run src.main --transport sse

# Using HTTP streaming
uvx run src.main --transport streamable-http

# Set log level
uvx run src.main --log-level DEBUG

# Run with custom configuration
uvx run src.main --transport stdio --log-level INFO

Available Tools

The MCP server provides comprehensive tools organized by functionality:

Collections Management

Function	Description	Parameters
get_all_collections()	Retrieve all accessible collections	None
get_collection_by_id(collection_id)	Get specific collection details	collection_id: str
create_collection(name)	Create a new collection	name: str
update_collection_name_or_owner(collection_id, name, owner_id)	Update collection properties	collection_id: str, name: str, owner_id: str
add_workflow_to_collection(collection_id, workflow_id)	Add workflow to collection	collection_id: str, workflow_id: str
remove_workflow_from_collection(collection_id, workflow_id)	Remove workflow from collection	collection_id: str, workflow_id: str
add_schedule_to_collection(collection_id, schedule_id)	Add schedule to collection	collection_id: str, schedule_id: str
remove_schedule_from_collection(collection_id, schedule_id)	Remove schedule from collection	collection_id: str, schedule_id: str
delete_collection(collection_id)	Delete a collection	collection_id: str

Workflow Operations

Function	Description	Parameters
get_all_workflows()	Retrieve all accessible workflows	None
get_workflow_by_id(workflow_id)	Get specific workflow details	workflow_id: str
update_workflow_name_or_comment(workflow_id, name, comment)	Update workflow properties	workflow_id: str, name: str, comment: str
transfer_workflow(workflow_id, new_owner_id)	Transfer workflow ownership	workflow_id: str, new_owner_id: str
get_workflow_jobs(workflow_id)	Get jobs for a workflow	workflow_id: str
start_workflow_execution(workflow_id, input_data)	Start workflow execution and return job ID	workflow_id: str, input_data: List[InputData]
execute_workflow_with_monitoring(workflow_id, input_data)	Execute workflow and monitor completion	workflow_id: str, input_data: List[InputData]
download_workflow_package_file(workflow_id, output_directory)	Download workflow package	workflow_id: str, output_directory: str
get_workflow_xml(workflow_id)	Extract workflow XML	workflow_id: str

User Management

Function	Description	Parameters
get_all_users()	Retrieve all accessible users	None
get_user_by_id(user_id)	Get specific user details	user_id: str
get_user_by_email(email)	Find user by email	email: str
get_user_by_name(name)	Find user by name	name: str
get_user_by_first_name(first_name)	Find user by first name	first_name: str
get_all_user_assets(user_id)	Get all assets owned by user	user_id: str
get_user_assets_by_type(user_id, asset_type)	Get specific asset types	user_id: str, asset_type: str
update_user_details(user_id, first_name, last_name, email)	Update user information	user_id: str, first_name: str, last_name: str, email: str
transfer_all_assets(user_id, new_owner_id, transfer_workflows, transfer_schedules, transfer_collections)	Transfer user assets	user_id: str, new_owner_id: str, transfer_workflows: bool, transfer_schedules: bool, transfer_collections: bool
deactivate_user(user_id)	Deactivate a user	user_id: str
reset_user_password(user_id)	Reset user password	user_id: str

Schedule Management

Function	Description	Parameters
get_all_schedules()	Retrieve all accessible schedules	None
get_schedule_by_id(schedule_id)	Get specific schedule details	schedule_id: str
deactivate_schedule(schedule_id)	Deactivate a schedule	schedule_id: str
activate_schedule(schedule_id)	Activate a schedule	schedule_id: str
update_schedule_name_or_comment(schedule_id, name, comment)	Update schedule properties	schedule_id: str, name: str, comment: str
change_schedule_owner(schedule_id, new_owner_id)	Change schedule ownership	schedule_id: str, new_owner_id: str

Job Monitoring

Function	Description	Parameters
get_all_job_messages(job_id)	Get messages for a specific job	job_id: str
get_job_by_id(job_id)	Get job details

---

README truncated. View full README on GitHub.