MCP server · Developer tools
Ariadne MCP server
by whyy9527
Lets your AI trace how a business term or endpoint flows across services, from frontend to Kafka.
Ariadne is a helper for teams whose code lives in many small services. It builds a map of the connections between your services, so you can ask your AI where something like createOrder actually lives. It is handy if you work on a Spring Boot or TypeScript microservice stack and keep losing track of which service talks to which.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to something else. This one connects your AI to a local map of your microservice code, so it can look up how a term or endpoint moves across your services. You ask in plain words, and the helper does the searching for you.
What this MCP server does
First, you point Ariadne at the folders of the services you want it to know about. It scans only the contract layer: GraphQL operations, REST endpoints, Kafka topics and frontend queries. It stores what it finds in a small local database on your machine. Then, when you ask your AI something like where createOrder lives, the AI asks Ariadne, and Ariadne returns a short list of the matching pieces across your services. You see a tidy chain in the chat, not a wall of code.
Click to zoomWhat you can do with it
- Trace a business term across frontend, gateway, services and Kafka
- Find which service owns a REST endpoint or GraphQL mutation
- See which Kafka topic connects a producer to a consumer
- Rescan your workspace when you pull new code
- Run a local evaluation of how well your queries are matched
- Try a built-in demo on a public sample project with no setup
Try asking your AI
- “Where does createOrder live across the stack?”
- “Which service handles POST /orders?”
- “Show me the chain for the owner term in the petclinic demo”
- “Which Kafka topic does billing-svc listen to?”
What it gives back to you
You get back a short, ranked list of matching pieces, grouped into clusters with a confidence score. Each line shows the service, the kind of thing it is (frontend mutation, GraphQL mutation, HTTP endpoint, Kafka topic or listener) and the name. The answer is kept small on purpose so it fits neatly in your AI chat. You can also get a summary of how well a set of test queries matched.
Before you start
What you need
- Python installed on your computer
- The pip package ariadne-mcp
- A config file listing the folders of the services you want indexed
- An AI coding assistant that supports MCP, such as Claude Code, Cursor or Windsurf
Good to know
It reads your local source folders to build its index, so point it only at repos you are comfortable having scanned.
Install it with your AI
Add Ariadne MCP server to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check Ariadne MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.
Who it's for
Developers and technical leads working on Spring Boot or TypeScript microservice stacks who need to trace how a term or endpoint moves between services.
