Patchworks MCP

Introduction

Using the Patchworks MCP server, your AI assistant (e.g. Claude, Gemini, or ChatGPT) can interact with Patchworks directly to triage issues, generate reports, and even run flows - all in natural language.

Whether you’re a merchant, partner, or developer, Patchworks MCP transforms how you work with your integrations.

Demo

Before looking at MCP in more detail, let's see how it can work in practice. The video below shows Claude identifying failed process flow runs from a given time period, summarising those flow failures, identifying failure patterns, recommending possible solutions, retrying failed runs, and reporting back on the outcome.

What is an MCP server?

MCP (Model Context Protocol) is an open protocol that enables secure, standardised connections between AI assistants (e.g. Claude) and external data sources or tools.

An MCP server acts as a bridge between your AI assistant and your business systems (e.g. Patchworks), allowing the AI to access real-time data and perform actions on your behalf, with precise control over what it can see and do. At a high level:

• MCP uses a client-server model, where an AI agent (the client) makes requests to an MCP server.

• The MCP server defines and exposes tools (e.g. get flow runs, summarise failed run, triage latest run failures) and resources (e.g. documentation, databases).

• AI agents use these tools and resources to perform actions, thereby expanding their abilities beyond their core language understanding.

You can see this in the illustration below:

Pre-loaded tools

Having installed Patchworks MCP locally, you can utilise ten pre-loaded tools:

• Track data through the platform

• Automate “Where is my order?” customer queries

• Generate reports from logs in seconds

• Identify errors that require intervention

• Instantly access all logs and payloads

• Run advanced root cause analysis

• Trigger flows directly

• Other system-level tools include “List all flows”, “Summarise failed run”, and “Download payloads”.

Example use cases

Team		Use-case
	Customer Support	“Show me all failed Shopify to NetSuite flows from last night and explain why.”
	Operations	“Re-run failed flows from yesterday.”
	Development	“Give me payload samples going into Order Flow X”

Why Patchworks MCP?

• AI-ready iPaaS Make integrations conversational and intelligent.

• Faster troubleshooting Automate triage & identify solutions

• Customisable Add your own tools alongside our pre-loaded set

• Safe & secure Per-tenant isolation, role-based access, and auditable tool calls.

• Future-proof Works with Claude, Gemini, ChatGPT, and any MCP-compatible client.

Implementation options

Right now, you can install Patchworks MCP locally and get started immediately. For details, please refer to Local installation & setup for Patchworks MCP.

Our hosted solution is in development and will be available in the near future - please keep an eye on our release notes for updates!