Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Read your own resume the way an ATS does and score it with a published, deterministic rubric.
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": {
"ats-engine": {
"command": "npx",
"args": [
"-y",
"@veriworkly/ats-engine-mcp"
]
}
}
}Run this in your terminal
claude mcp add ats-engine -- npx -y @veriworkly/ats-engine-mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"ats-engine": {
"command": "npx",
"args": [
"-y",
"@veriworkly/ats-engine-mcp"
]
}
}
}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": {
"ats-engine": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@veriworkly/ats-engine-mcp"
]
}
}
}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 6, 2026
The registry name was verified with the GitHub account VeriWorkly, 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 (0.15.1) reached the registry 9 days 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, yontu
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.
Türkçe yazı denetimi: TDK kuralları, yapay zekâ izleri, metin türüne göre üslup.
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.
An MCP server that lets an AI assistant (Claude, Cursor, VS Code Copilot and others) read your own resume the way an applicant tracking system (ATS) does, and score it with @veriworkly/ats-engine's published, deterministic rubric.
Setup for each client, every tool and its inputs, and example prompts: [docs.veriworkly.com/ats-engine/tools/mcp](https://docs.veriworkly.com/ats-engine/tools/mcp).
Ask your assistant things like "check my resume at ~/Documents/cv.pdf", "how well does it match this job posting?", "why did it fail the date check?" or "show me how an ATS reads my resume".
The score comes from the rubric (RUBRIC.md), not from a model. The same file always gets the same score. The assistant explains the result and helps you fix what failed.
You need Node.js 22.12 or later. Every client below runs the server with npx -y @veriworkly/ats-engine-mcp.
claude mcp add ats-engine -- npx -y @veriworkly/ats-engine-mcp
On native Windows (not WSL), wrap npx in cmd /c:
claude mcp add ats-engine -- cmd /c npx -y @veriworkly/ats-engine-mcp
Open Settings → Developer → Edit Config, add the server to claude_desktop_config.json, and restart Claude Desktop:
{
"mcpServers": { "ats-engine": { "command": "npx", "args": ["-y", "@veriworkly/ats-engine-mcp"] } } }
Add it to ~/.cursor/mcp.json (every project) or .cursor/mcp.json (one project):
{
"mcpServers": { "ats-engine": { "command": "npx", "args": ["-y", "@veriworkly/ats-engine-mcp"] } } }
Add it to .vscode/mcp.json in your workspace, or run MCP: Add Server from the Command Palette:
{
"servers": { "ats-engine": { "type": "stdio", "command": "npx", "args": ["-y", "@veriworkly/ats-engine-mcp"] } } }
| Tool | Input | Returns |
|---|---|---|
check_resume | path or text; optional job_path or job_text; optional region; optional target_ats | Readiness score (0–100), verdict, category scores (writing style included), every failed check with its evidence and fix, and the fields an ATS stores (name, contact, roles, education, skills; the structured parsed also holds certifications and spoken languages with their CEFR level). With a posting: job match, requirements and keywords too. Then advice, which is not scored. |
match_job | path or text; job_path or job_text (required); optional region | Job match score, each requirement judged met / partial / missing / unverifiable with evidence, and the missing keywords, hard skills and soft skills apart (soft skills weigh less). |
explain_rule | rule_id; optional region | One rubric rule: category, severity, what it checks, points, how to fix it. With a region, as that country weighs it (a photo is worth 6 points in the US and is not scored in Germany). An unknown id lists the valid ones. |
extract_text | path or text; optional region | The text in the order an ATS reads it, line by line, plus what the layout measured (columns, tables, hidden text). For "why did it read my resume like this?" |
Every tool returns readable text for the assistant and its result as structured JSON (structuredContent, described by each tool's outputSchema).
The resource rubric://default is the whole rubric as JSON.
Inputs.
.pdf, .docx, .html, .txt, .md, or a .json JSON Resume or ats-resume document. Postings: .txt, .md, .pdf, .docx, or a saved .html page; a job_path of any other type is refused, since a posting's words come back in the answer.~/ is read as your home folder; any other relative path is read from the folder the server was started in.text and job_text may be up to 200 000 characters. A posting, pasted or read from job_path, is scored on its first 20 000 characters; a longer one is cut there, and check_resume's parsingWarnings says so.\\host\share\…; on Windows also //host/share/…). So is a PDF with no text layer: an ATS cannot read a scan either.language (check_resume, match_job) is en, de, fr, hi, es or pt; en reads English only. Without it, the language is detected from the resume and from the posting. It sets the language of both, so give it only when the resume was read in the wrong one: en with a German posting reads the posting as English too.region is US, GB, DE, FR, IN, ES, BR, PT, MX, AR, CO or CL. Without it, the region is inferred from the resume.target_ats is greenhouse, lever or taleo. It adds what that vendor documents publicly, each note with a link to the vendor's page. It never changes the score.Advice. check_resume ends with advice, a list that is never scored. For a file (not pasted text) it covers the name (Resume_final_v3 (2).pdf reads as a draft; a Firstname-Lastname-Resume.pdf name is suggested), a size over 2 MB, a password, and tracked changes or comments left in a Word document. For a US resume it also covers details that can invite age bias. With target_ats it adds the vendor's notes.
The server runs on your computer, over stdio. It makes no network requests and calls no AI model. It reads only the files you name in a request, a PDF, DOCX or HTML file in a separate process that is stopped after 60 seconds or when the request is cancelled, as many at once as your computer has CPU cores, and nothing leaves your machine except what your assistant itself sends to its model provider: the tool results it reads, which include text from your resume.
[!IMPORTANT]
This is a tool for candidates to check their own resume. Do not use it to screen, rank or
reject other people. Using it that way may make it an automated employment decision tool under
laws such as New York City Local Law 144 and the EU AI Act, which carry duties this package does
not meet for you. See Intended use.
A score measures how well a resume parses and reads. It says nothing about the person.
git clone https://github.com/VeriWorkly/ats-engine.git
cd ats-engine npm ci npm run build claude mcp add ats-engine -- node "$PWD/packages/mcp/dist/index.js"
MIT