Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
OpenAPI lifecycle guard and MCP sidecar for policy-driven API orchestration.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"x-openapi-flow": {
"command": "npx",
"args": [
"-y",
"x-openapi-flow"
]
}
}
}Run this in your terminal
claude mcp add x-openapi-flow -- npx -y x-openapi-flowPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"x-openapi-flow": {
"command": "npx",
"args": [
"-y",
"x-openapi-flow"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"x-openapi-flow": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"x-openapi-flow"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account tiago-marques, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (1.7.4) reached the registry 6 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, First Sale Scout
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Playbooks and a 14-day checklist for founders winning their first paying customers.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
🚀 2,100+ downloads in the first 3 weeks!
npx x-openapi-flow init --suggest-transitions
See your API lifecycle come alive from your OpenAPI spec, with one simple command
Validate, document, and generate flow-aware SDKs automatically.
openapi.json → describes your API
openapi.x.json → describes how to use it (flows)
x-openapi-flow adds a declarative state machine to your OpenAPI spec.
Model resource lifecycles, enforce valid transitions, and generate flow-aware artifacts for documentation, SDKs, and automation.
Define stateful workflows and lifecycle transitions directly inside your OpenAPI operations:
{
"operationId": "createOrder", "x-openapi-flow": { "version": "1.0", "id": "create-order", "current_state": "created", "description": "Creates an order and starts the lifecycle", "transitions": [ { "transition_id": "order-created-to-paid", "trigger_type": "synchronous", "condition": "Payment is confirmed", "decision_rule": "payOrder:response.200.body.payment_status == 'approved'", "target_state": "paid", "next_operation_id": "payOrder", "operation_role": "mutate", "prerequisite_operation_ids": ["createOrder"], "evidence_refs": [ "payOrder:response.200.body.payment_status" ], "propagated_field_refs": [ "createOrder:response.201.body.order_id" ], "failure_paths": [ { "reason": "Payment denied", "target_state": "payment_failed", "next_operation_id": "getOrder" } ] } ] } }
This flow defines an order lifecycle directly inside your OpenAPI:
created statepaid when payment is confirmedInstead of manually orchestrating API calls, the workflow is fully described alongside your API specification.
Building APIs is cheap. Building complex, multi-step APIs that teams actually use correctly is hard.
Teams face recurring problems:
x-openapi-flow exists to solve these pains: it makes lifecycles explicit, validates transitions automatically, and generates flow-aware docs and SDKs — so teams move faster, make fewer mistakes, and ship confident integrations.
Turn your OpenAPI spec into a single source of truth for API behavior:
export-llm-flows) — or call it directly as an MCP tool — so an agent like Claude Code knows the exact call order, decision rules, and field refs to implement an integration, without re-deriving them from human docsPrefer no local setup? Open the minimal runtime-guard demo directly in your browser:
Once open, run:
npm install
npm run start
Then in another terminal:
curl -s -X POST http://localhost:3110/orders
curl -i -X POST http://localhost:3110/orders/ /ship
Expected: 409 INVALID_STATE_TRANSITION.
Fastest way to see value (guided scaffold):
npx x-openapi-flow quickstart
cd x-openapi-flow-quickstart npm install npm start
Optional runtime:
npx x-openapi-flow quickstart --runtime fastify
Then run:
curl -s -X POST http://localhost:3110/orders
curl -i -X POST http://localhost:3110/orders/ /ship
Expected: 409 INVALID_STATE_TRANSITION.
Initialize flow support in your project:
npx x-openapi-flow init
npx x-openapi-flow init --suggest-transitions
After regenerating your OpenAPI file, apply and validate the flow (optional):
npx x-openapi-flow apply openapi.yaml --out openapi.flow.yaml
npx x-openapi-flow validate openapi.flow.yaml --profile strict --strict-quality
This will:
💡 Tip: run this in CI to enforce API workflow correctness
For larger APIs, you can define flow rules by resource (with shared transitions/defaults) and reduce duplication in sidecar files.
See: Sidecar Contract
Use the official reusable action to validate lifecycle rules in CI with a single step:
- name: Validate OpenAPI flow rules
uses: tiago-marques/x-openapi-flow@v1 with: openapi-file: openapi.flow.yaml profile: strict strict-quality: "true"
Integration guide: GitHub-Actions-Integration.md
Here’s a real-world payment lifecycle represented in x-openapi-flow:
CREATED -> AUTHORIZED -> CAPTURED -> REFUNDED
Generate a visual graph of the lifecycle:
npx x-openapi-flow graph openapi.flow.yaml --format mermaid
Resulting diagram:
graph TD
CREATED --> AUTHORIZED AUTHORIZED --> CAPTURED CAPTURED --> REFUNDED
This visualization makes your API workflow explicit, easy to communicate, and ready for documentation or demos.
Create a TypeScript or Python SDK that respects your API’s lifecycle and transition rules, following best practices seen in leading companies like Stripe and Adyen:
npx x-openapi-flow generate-sdk openapi.flow.yaml --lang typescript --output ./sdk
npx x-openapi-flow generate-sdk openapi.flow.yaml --lang python --output ./sdk
Example usage (TypeScript):
const payment = await sdk.payments.create({ amount: 1000 });
await payment.authorize(); await payment.capture();
Example usage (Python — zero-dependency, stdlib urllib-backed client, generated under ./sdk/src):
from src import FlowApiClient
from src.http_client import UrllibHttpClient
client = FlowApiClient(UrllibHttpClient("https://api.example.com")) payment = client.payment.create({"body": {"amount": 1000}}) payment = payment.authorize() payment = payment.capture()
This SDK guides developers through valid transition paths, following patterns used by market leaders to ensure safe and intuitive integrations.
CI validation is important, but production safety needs request-time enforcement.
x-openapi-flow now includes an official runtime guard for Node.js that can block invalid state transitions during request handling.
operationId (when available) or by method + route409 error payloadsInstall and use directly in your API server:
const {
createExpressFlowGuard, createFastifyFlowGuard, createHonoFlowGuard, } = require("x-openapi-flow/lib/runtime-guard");
Express example:
const express = require("express");
const { createExpressFlowGuard } = require("x-openapi-flow/lib/runtime-guard"); const openapi = require("./openapi.flow.json");
const app = express();
app.use( createExpressFlowGuard({ openapi, async getCurrentState({ resourceId }) { if (!resourceId) return null; return paymentStore.getState(resourceId); // your DB/service lookup }, resolveResourceId: ({ params }) => params.id || null, }) );
Fastify example:
const fastify = require("fastify")();
const { createFastifyFlowGuard } = require("x-openapi-flow/lib/runtime-guard"); const openapi = require("./openapi.flow.json");
fastify.addHook( "preHandler", createFastifyFlowGuard({ openapi, async getCurrentState({ r
Only the beginning is shown; read the rest in the repo