logicapps-mcp
Enables managing and debugging Azure Logic Apps through natural language, with tools for listing, debugging, creating, updating, and deleting workflows.
README
Azure Logic Apps MCP Server
<img src="https://raw.githubusercontent.com/benc-uk/icon-collection/master/azure-icons/Logic-Apps.svg" alt="Azure Logic Apps" width="80" align="right">
Manage and debug Azure Logic Apps using natural language. Ask your AI assistant to investigate failed runs, explain workflows, or make changes—no portal clicking required.
You: Why did my order-processing workflow fail this morning?
AI: Looking at the run history... Found a failed run at 10:15 AM.
The HTTP action "Call-Payment-API" failed with 503 Service Unavailable.
The payment service at api.payments.com was down for 3 minutes.
You: Add retry logic to that action - 3 attempts with exponential backoff.
AI: Done. Updated the workflow with retry policy. Want me to test it?
Works with GitHub Copilot, Claude Desktop, or any MCP-compatible AI client. Supports both Consumption and Standard Logic Apps.
Quick Start
# 1. Install
npm install -g logicapps-mcp
# 2. Login to Azure
az login
# 3. Configure your AI assistant (example for VS Code)
Add to .vscode/mcp.json in your workspace:
{
"servers": {
"logicapps": {
"type": "stdio",
"command": "logicapps-mcp"
}
}
}
Reload VS Code and start chatting with Copilot about your Logic Apps!
Cloud MCP Server: Need a hosted deployment? See the Getting Started Guide for Azure deployment instructions.
Features
- 40 Tools for Logic Apps operations: list, debug, create, update, delete workflows
- Dual SKU Support: Works with both Consumption and Standard Logic Apps
- Run Debugging: Trace failures through actions, loops, and scopes
- Write Operations: Create workflows, run triggers, cancel runs
- Connector Support: Discover connectors, create connections
Example Prompts
"List my Logic Apps in subscription xyz"
"Show failed runs from the last 24 hours"
"What went wrong in run ID abc123?"
"Add retry logic to the HTTP action"
"Disable the order-processing workflow"
Documentation
- Getting Started Guide - Setup for Claude, Copilot, Cloud MCP Server
- Available Tools - All 40 tools with descriptions
- Configuration - Environment variables, auth, SKU differences
- Changelog - Release history
Development
npm run dev # Run in development mode
npm test # Run unit tests
npm run test:integration # Run integration tests (requires Azure setup)
npm run test:all # Run all tests
Integration Testing
Integration tests run against real Azure resources. They auto-discover your subscriptions and Logic Apps:
az login # Login to Azure
npm run test:integration # Tests find resources automatically
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.