Runs on Cloudflare Workers, providing a serverless endpoint for extracting acceptance criteria from requirement documents.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Acceptance Criteria Extractor extract acceptance criteria from 'Given user is registered, When they login, Then they see dashboard.'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Acceptance Criteria Extractor is a Cloudflare Workers + TypeScript app for extracting explicitly written acceptance criteria from requirement documents, user stories, feature specifications, testing notes, or task descriptions.
App name: Acceptance Criteria Extractor
App slug: acceptance-criteria-extractor
Version: 1.0.0
Cloudflare Worker name: acceptance-criteria-extractor
MCP endpoint: /mcp
Support email: sidcraigau@gmail.com
Related MCP server: refine-backlog-mcp
The only exposed MCP tool is extract_acceptance_criteria.
It accepts source_text and returns structured criteria, source fragments, extracted Given/When/Then pieces where present, criteria_count, and structured errors.
The tool is read-only, stateless, deterministic, and does not call external APIs. It does not generate new acceptance criteria, evaluate whether criteria are sufficient, run tests, write to databases, create issues, send email, submit forms, or modify external systems.
npm install
npm run typecheck
npm run build
npm run test:mcp:local
npm run test:mcp:productionnpm run devRoutes:
GET /
GET /health
POST /mcp
Required MCP methods:
initialize
tools/list
tools/call
This repository includes the Gate 3 Review Shell routes, challenge route, and production MCP regression command.
This server cannot be deployed
Check AI work against requirements and return structured verdicts, findings, and repair steps.
Extrait des champs structures (texte, nombre, date) depuis un texte libre.
Extract structured data points from research papers and other documents with an LLM.
High-fidelity PDF to structured Markdown conversion and document field extraction.
