AI-Automation

Welcome to the AI Automation workspace – a curated collection of cutting-edge, production-ready AI solutions for enterprise productivity, document intelligence, workflow automation, and developer augmentation.

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

View docs

Command

claude mcp add --transport stdio er-jyotsnabharti-ai-automation node server.js \
  --env CLAUDE_API_KEY="your_claude_api_key_here" \
  --env COPILOT_API_KEY="your_copilot_api_key_here" \
  --env AGENTPASS_API_KEY="your_agentpass_api_key_here"

How to use

The AI Automation workspace presents a prebuilt MCP (Model Context Protocol) server designed to host MCP endpoints for AgentPass AI workflows. This server enables visual creation and hosting of MCP endpoints, which can be invoked by tools such as VS Code Copilot and Claude to perform real-time tool execution inside developer environments. Once running, you can connect the MCP server to your automation workflows (n8n, AgentPass AI, or other orchestrators) to orchestrate model-driven actions, run agent-powered tasks, and execute custom endpoints that integrate with your tooling stack. The included capabilities focus on developer augmentation, tool orchestration, and workflow automation, enabling you to run MCP-based contexts with AgentPass AI as the orchestration layer.

How to install

Prerequisites:

Node.js (14.x or newer) and npm/yarn installed
Access to AgentPass AI and any required API keys for Claude, Copilot, or Gemini integrations

Steps:

Clone the repository or prepare your environment where the MCP server will run.
Install dependencies:
- npm install
- or yarn install
Configure environment variables (example shown in mcp_config):
- AGENTPASS_API_KEY: your AgentPass AI API key
- CLAUDE_API_KEY: your Claude API key (if using Claude integration)
- COPILOT_API_KEY: your Copilot API key (if using Copilot integration)
Start the MCP server:
- npm run start
- or node server.js
Verify the server is running by checking logs or hitting the configured health/endpoint route.
Integrate with your workflow orchestrator (n8n, AgentPass AI visual editor, etc.) by importing the MCP endpoint definitions and connecting to the host/port where this server is exposed.

Additional notes

Tips and considerations:

Ensure network access to external services (Claude, Copilot, Gemini) as required by your configured endpoints.
Keep API keys secure; use environment variable management or secret stores in your deployment environment.
If you modify endpoint definitions, restart the MCP server to apply changes.
Refer to AgentPass AI documentation for best practices on visual MCP endpoint design and tool orchestration.
If you encounter port conflicts, adjust the server listen port in your configuration and update the access URL in your orchestrators.
For local development, use a VPN or secure tunnel if your endpoints need to be exposed to external services.
Enable logging with appropriate verbosity to diagnose integration issues between Copilot, Claude, and MCP endpoints.

Related MCP Servers

mcp -azure-devops

339

An MCP server for Azure DevOps

snippy

106

🧩 Build AI-powered MCP Tools with Azure Functions, Durable Agents & Cosmos vector search. Features orchestrated multi-agent workflows using OpenAI.

codebase-context

Local-first Second brain for AI agents working on your codebase - detects your team coding conventions and patterns, brings in persistent memory, code-generation checks, and hybrid search with evidence scoring. Exposed through CLI and MCP server.

shortcuts

Shortcuts + MCP = ♥️

packt-netops-ai-workshop

🔧 Build Intelligent Networks with AI

unity

A Unity MCP server that allows MCP clients like Claude Desktop or Cursor to perform Unity Editor actions.