# whyy9527/ariadne [Health: Active]
**Category:** ๐๏ธ Databases
**Repository:** https://github.com/whyy9527/ariadne
**GitHub Stars:** 2
**Views:** 0
**Installs:** 0
**Upvotes:** 0
**Directory Page:** https://allmcps.com/mcp/whyy9527-ariadne
## Description
Cross-service API dependency graph for microservice codebases. Give it a business term or endpoint name; get back a ranked chain of GraphQL operations, REST endpoints, Kafka topics, and frontend queries across all services. Offline, local SQLite + TF-IDF + optional embeddings.
## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `uvx` (confidence: high):
```json
"mcpServers": {
"ariadne": {
"command": "uvx",
"args": ["ariadne-mcp"]
}
}
```
## Documentation & README
# Ariadne
[](LICENSE)
[](https://modelcontextprotocol.io)
[](https://glama.ai/mcp/servers/whyy9527/ariadne)
[](https://github.com/punkpeye/awesome-mcp-servers#-developer-tools)
> Ariadne's thread โ a way out of the microservice maze.
Cross-service API dependency graph for Spring Boot + TypeScript
microservice stacks. MCP stdio server for AI coding assistants
(Claude Code, Cursor, Windsurf), with a CLI twin. Local SQLite + TF-IDF.
Zero ML dependencies.
70-second deterministic terminal walkthrough. Reproduce it from
[`docs/demo.tape`](https://github.com/whyy9527/ariadne/blob/HEAD/docs/demo.tape).
---
## What it does
Indexes the *contract layer* โ GraphQL mutations, REST endpoints, Kafka
topics, frontend queries. Nothing else. That's why results fit an AI
context window.
Ask Claude *"where does createOrder live across the stack?"* and
`query_chains` returns:
```
Top Cluster #1 [confidence: 0.91]
Services: gateway, orders-svc, billing-svc, web
- [web] Frontend Mutation: createOrder
- [gateway] GraphQL Mutation: createOrder
- [orders-svc] HTTP POST /orders: createOrder
- [orders-svc] Kafka Topic: order-created
- [billing-svc] Kafka Listener: order-created โ chargeCustomer
```
The response is intentionally bounded for an AI context window. See the
[reproducible public-stack benchmark](https://github.com/whyy9527/ariadne/blob/HEAD/BENCHMARKS.md) for measured retrieval,
serialized token, and timing results against `rg` and `grep`.
Current public-stack benchmark (48 reviewed queries across Spring REST,
GraphQL/TypeScript, Kafka, and FastAPI):
| Backend | Top-1 | Top-3 | MRR | Warm query | Mean output |
|---|---:|---:|---:|---:|---:|
| Ariadne | 64.6% | 70.8% | 0.677 | <0.3 ms | 157 tokens |
| `rg` | 37.5% | 56.2% | 0.510 | ~9 ms | 591 tokens |
| `grep` | 37.5% | 56.2% | 0.510 | ~9 ms | 591 tokens |
[Full methodology and per-stack results](https://github.com/whyy9527/ariadne/blob/HEAD/BENCHMARKS.md) ยท
[raw JSON evidence](https://github.com/whyy9527/ariadne/blob/HEAD/benchmarks/results.json)
This corpus is operation-name-heavy and measures deterministic contract lookup
compatibility. It is not yet a natural-language relevance benchmark.
Supports: GraphQL ยท Spring HTTP/Kafka/RestClient ยท Python FastAPI ยท TypeScript
Apollo/fetch/axios ยท Cube.js.
---
## Try it in 30 seconds (zero config)
```bash
pip install ariadne-mcp
ariadne-mcp demo
```
Clones [`spring-petclinic-microservices`][petclinic] into
`~/.cache/ariadne-mcp/demo`, scans it, and prints the top cluster for
`owner` โ a real cross-service call chain. No config file, no workspace
setup.
Did Ariadne find the chain you expected? Share one minute of
[structured feedback][feedback-form]. Ariadne sends no usage data automatically;
the form opens only when you choose to submit it.
[petclinic]: https://github.com/spring-petclinic/spring-petclinic-microservices
[feedback-form]: https://github.com/whyy9527/ariadne/issues/new?template=usage-feedback.yml
---
## Install on your own workspace
```bash
pip install ariadne-mcp
cp "$(python -c 'import ariadne_mcp, os; print(os.path.join(os.path.dirname(ariadne_mcp.__file__), "ariadne.config.example.json"))')" ariadne.config.json
# edit ariadne.config.json (list the repos you want indexed)
ariadne-mcp install ariadne.config.json ~/your-workspace
```
Restart Claude Code. `install` is idempotent โ re-run after pulling new
code, or let the assistant call `rescan` on a `stale_warning`.
After your first real query, you can optionally send
[closed-ended usage feedback][feedback-form]. No source, query, or usage data is
transmitted by Ariadne itself.
---
## Config
```json
{ "repos": [
{ "path": "../gateway" },
{ "path": "../orders-svc" },
{ "path": "../web" }
]}
```
Scanners are inferred from each repo's top-level files
(`pom.xml` / `build.gradle` / `package.json` / SDL). See
[`docs/CONFIG.md`](https://github.com/whyy9527/ariadne/blob/HEAD/docs/CONFIG.md) for the detection table and override
syntax.
---
## Reproducible public samples
Each sample pins an upstream commit, scans real service source, runs one query,
and verifies manually reviewed node IDs:
| Example | Contract path |
|---|---|
| [`spring-petclinic`](https://github.com/whyy9527/ariadne/blob/HEAD/examples/spring-petclinic/) | Spring REST gateway โ service |
| [`one-platform`](https://github.com/whyy9527/ariadne/blob/HEAD/examples/one-platform/) | GraphQL/TypeScript services |
| [`kafka-microservices`](https://github.com/whyy9527/ariadne/blob/HEAD/examples/kafka-microservices/) | Kafka producer โ consumer |
| [`fastapi-microservices`](https://github.com/whyy9527/ariadne/blob/HEAD/examples/fastapi-microservices/) | Python FastAPI routes |
Run one from a source checkout:
```bash
python examples/run.py kafka-microservices
```
---
## Evaluate ranking
Keep a JSONL judgment list for queries that matter to your workspace:
```jsonl
{"hint":"createOrder","expected_node_ids":["gateway::gql::m::createOrder"],"k":3}
{"hint":"owner","expected_node_ids":["customers::http::GET /owners/{ownerId}"],"match":"any","k":5}
```
Run it against a built DB:
```bash
ariadne-mcp --db .ariadne/ariadne.db eval eval/queries.jsonl --top 3 --min-hit-rate 0.8
```
The command evaluates top-k hit rate and MRR using a stable internal candidate
depth, and exits non-zero when a configured threshold fails. Add
`--feedback-db .ariadne/feedback.db` to include local feedback reranking in the
eval.
---
Architecture, MCP tools, scoring math, feedback boost โ
[`docs/ARCHITECTURE.md`](https://github.com/whyy9527/ariadne/blob/HEAD/docs/ARCHITECTURE.md). Custom scanners (Go,
Rust, anything) โ [`docs/CUSTOM_SCANNERS.md`](https://github.com/whyy9527/ariadne/blob/HEAD/docs/CUSTOM_SCANNERS.md).
Maintainer adoption snapshots โ [`docs/ADOPTION_METRICS.md`](https://github.com/whyy9527/ariadne/blob/HEAD/docs/ADOPTION_METRICS.md).