How do I use Stack AI MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Stack AI MCP Server run the data analysis workflow for my latest sales report" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Stack AI Cover

Stack AI MCP Server

A Model Context Protocol (MCP) server that connects to Stack AI workflows, allowing you to run your Stack AI workflows directly through MCP-compatible clients.

Features

Run Stack AI workflows through MCP
Pass user inputs to your workflows
Receive workflow results as structured responses

Setup

Prerequisites

You'll need the following Stack AI credentials:

STACK_AI_ORG_ID: Your Stack AI organization ID
STACK_AI_PROJECT_ID: Your Stack AI project ID
STACK_API_KEY: Your Stack AI API key

Installation

Clone the repository to your local machine:
git clone https://github.com/stackai/stack-ai-mcp.git
Navigate to the project directory:
cd stack-ai-mcp
Install the dependencies:
npm install

Claude Desktop Configuration

To use the Stack AI MCP Server with Claude Desktop, add the following to your claude_desktop_config.json:

{ "mcpServers": { "stack-ai-workflow": { "command": "node", "args": ["/absolute/path/to/stack-ai-mcp/src/main.ts"], "env": { "STACK_AI_ORG_ID": "your_org_id_here", "STACK_AI_PROJECT_ID": "your_project_id_here", "STACK_API_KEY": "your_api_key_here" } } } }

Replace /absolute/path/to/stack-ai-mcp/src/main.ts with the actual absolute path to your cloned repository, and replace the environment variable values with your actual Stack AI credentials.