Stack AI

Provides an MCP interface to run Stack AI workflows by passing inputs and receiving structured results.

typescript

0

GitHub Stars

typescript

Language

6 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": {
    "stackai-stack-ai-mcp": {
      "command": "node",
      "args": [
        "/absolute/path/to/stack-ai-mcp/src/main.ts"
      ],
      "env": {
        "STACK_API_KEY": "YOUR_API_KEY",
        "STACK_AI_ORG_ID": "YOUR_ORG_ID",
        "STACK_AI_PROJECT_ID": "YOUR_PROJECT_ID"
      }
    }
  }
}

Stack AI MCP Server lets you run Stack AI workflows through MCP-compatible clients. It bridges your Stack AI workflows with MCP, enabling you to pass user inputs, execute workflows, and receive structured results in your MCP integrations.

How to use

You interact with the Stack AI MCP Server using an MCP client that supports stdio-based servers. Configure your client to launch the local MCP server as a stdio process using the provided command and arguments. When you start a workflow, your client passes inputs to the server, which runs the corresponding Stack AI workflow and returns the results in a structured format that your client can consume. Use this setup to integrate Stack AI workflows into your existing MCP-enabled automation, chatbots, or tooling workflows.

How to install

Prerequisites: You need Node.js installed on your machine. You also require Stack AI credentials to access your workflows.

# Install dependencies
npm install

# Start the MCP server in development mode
npm run dev

Additional configuration and notes

Claude Desktop configuration is provided as an example to wire the MCP server into Claude Desktop. You will run the MCP server locally and point Claude to the absolute path of the server entry script. Ensure you replace placeholder paths and credentials with your actual values.

{
  "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"
      }
    }
  }
}

Available tools

run_workflow

Executes a Stack AI workflow through the MCP server, taking inputs from the client and returning the workflow results.

pass_inputs

Transfers user inputs from the MCP client to the active Stack AI workflow.

return_results

Formats and returns the Stack AI workflow output as a structured response to the MCP client.