Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Runs on your computer
Vigilis
Overview
Description from the maker (original English)
Gate AI-written tests: heal safe drift, refuse to hide real bugs, sign a verifiable receipt.
PopNx MCP’s three pillars
These three are never merged into one score: opinions, measurements and popularity are different things.
- User voiceiNo reviews yetReviews open together with accounts in a later step
- Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
- UsageiVery new↓ 62/wk · ★ –
What you can do with it
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
- Connection: Runs on your computer
- Transport: stdio
- Category: Other
- You need to fill in: ANTHROPIC_API_KEY
Install
Pick the AI app you use, then copy the settings.
Before you install
- Basic checks: 1 of 1 passed
- Runs on your computer with your user’s permissions (files, network, apps).
- You fill in yourself:
ANTHROPIC_API_KEY
Values marked secret are keys to your account. Never share them or paste them into a chat.
You need
- npmNode.js installed (for the npx command)
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": {
"vigilis": {
"command": "npx",
"args": [
"-y",
"vigilis-mcp"
],
"env": {
"ANTHROPIC_API_KEY": "your-value"
}
}
}
}Run this in your terminal
claude mcp add vigilis --env ANTHROPIC_API_KEY=your-value -- npx -y vigilis-mcpFill in the empty values before running it.
Or copy the settings yourself
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"vigilis": {
"command": "npx",
"args": [
"-y",
"vigilis-mcp"
],
"env": {
"ANTHROPIC_API_KEY": "your-value"
}
}
}
}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.
Or copy the settings yourself
Paste into .vscode/mcp.json in your project
{
"servers": {
"vigilis": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"vigilis-mcp"
],
"env": {
"ANTHROPIC_API_KEY": "your-value"
}
}
}
}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.
Values you fill in
- Pay-as-you-go Anthropic API key used to run the Vigilis agent (not a Claude.ai subscription).
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
What it can do
Runs on your computer; the tool list appears in your AI app after you install it.
Basic checksi
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 8, 2026
- ✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account piyushpathakqa, which owns the repo
- … Not checked yet
Still maintained
We have not read this repo from GitHub yet
- … Not checked yet
Has a licence
We have not read this repo from GitHub yet
- – Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
- – Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
- … Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints
Compared with others in Otheri
- More stars than 0% of the other 18513 servers in this category
- Published to the registry more recently than 13% of the other 18513 servers in this category
- Basic checks equal to or better than 100% of the other 18513 servers in this category
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
Common questions
Is Vigilis safe?
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.
What keys or codes does it need?
You need to fill in: ANTHROPIC_API_KEY
Does it run on my computer or in the cloud?
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).
Is it still maintained?
The GitHub repo last changed –, and the latest version (0.4.1) reached the registry 4 months ago.
Which apps can use it?
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
What can I use instead?
In the same category: Spec Driven Development, Remote Desktop Commander, Cape Winelands Visit Planner
Alternatives
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Remote Desktop Commander
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Runs in the cloud✓ desktopcommander.app
Cape Winelands Visit Planner
Cape Winelands wine farm finder and day-route planner
Runs in the cloud✓ aiagenttools.co.za
README from the maker
Open the README
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.
👁️ Vigilis
The QA gate for AI-written code.
It heals safe test drift, refuses real regressions , and signs every decision into an independent, verifiable receipt.
The problem
Tell any coding agent to *"make CI pass"* and the cheapest path to green is deleting the test that caught the bug. AI now writes and fixes tests on its own — so the only question that matters is: can you trust what it did?
Vigilis answers it. Point it at the Playwright, Cypress, or Selenium suite you already have. When a test breaks, it decides:
- Cosmetic drift (a renamed selector) → it heals the locator, re-runs to verify green, opens a PR.
- A real behaviour change (checkout total went from
$49to$0) → it refuses to touch the test, fails the gate, and surfaces the bug instead of burying it.
And every decision is sealed into a signed, offline-verifiable receipt by an independent notary — so a refusal is something you can *prove*, not just claim.
Self-healing is the wedge. Verifiable proof is the point.
Where teams point it: gate AI-written code · self-heal without hiding bugs · auditable test runs · audit-grade evidence for SOX / payment controls · agent-native (MCP). → see the use cases
See it refuse a real bug
The agent ran the spec, saw it fail, checked that the selectors were all correct, concluded the app's login was genuinely broken, and refused to heal — then sealed a receipt anyone can verify offline.
Quickstart
npm i -D vigilis # in your Playwright / Cypress / Selenium projectnpx playwright install chromium # one-time, for browser automation export ANTHROPIC_API_KEY=sk-ant-... # a pay-as-you-go API key (not a Claude.ai subscription)
npx vigilis init # scaffold vigilis.config.json (auto-detects your framework) npx vigilis generate https://your-app.com --run # explore the app → write + run a real spec npx vigilis heal https://your-app.com --spec tests/login.spec.ts # heal drift → verify green → PR (refuses real bugs)
already have a suite running in CI? attest the run you just did — no API key, no secrets:
npx playwright test --reporter=json > report.json npx vigilis attest-run report.json --commit $GITHUB_SHA --exit-code $? npx vigilis verify .vigilis/attestation/qa-run-*.json # offline: chain intact, or broken at record #N
Runs in your CI on your own key + chromium. About 10¢ per run on the fast model (--model claude-haiku-4-5); Opus by default for quality.
Why it's different
| Vigilis | |
|---|---|
| Heals | Rewrites the locator for cosmetic drift, re-verifies green, opens a PR. |
| Refuses | A real regression is a hard, fail-closed contract — it will not weaken the assertion that caught the bug. |
| Proves | Every heal *and* every refusal is sealed into an independent, offline-verifiable receipt (via Treeship). |
Attestation is verifiable and auditable — it proves *what the agent did*, in order, unaltered. It does not claim the agent's judgement was correct. That honesty is the point: Vigilis improves signal, it doesn't hide failures.
Why a refusal is credible: no layer grades its own work. The actor (any agent) writes the code and tests; Vigilis judges the behaviour and gates the deploy; an independent notary (Treeship) signs the verdict. Vigilis never signs its own homework — which is what makes the proof worth anything to someone who doesn't already trust you.
Optional: alert on a refusal
On a real-bug refusal, Vigilis can post a Slack alert and file a deduplicated Linear ticket — each linking the signed receipt. Off by default; a no-op until you set SLACK_WEBHOOK_URL / LINEAR_API_KEY. See docs/REFUSAL-ACTIONS.md.
Drive it from Claude (MCP)
The same tools ship as an MCP server (vigilis-mcp, in the official MCP registry) — generate / triage / heal straight from Claude Desktop, Claude Code, or Cursor. Add it to your MCP client config:
{"mcpServers": { "vigilis": { "command": "npx", "args": ["-y", "vigilis-mcp"], "env": { "ANTHROPIC_API_KEY": "sk-ant-..." } } } }
Full setup: docs/MCP.md.
Provenance receipts
Receipts work out of the box with zero secrets — no account, no API key, no network:
- `vigilis attest-run ` seals *any* test run (not just Vigilis's own) into a receipt: it hash-chains the Playwright report's digest, the commit SHA, and the runner's exit code into a tamper-evident bundle under
.vigilis/attestation/. Drop it after your existingplaywright teststep in CI and every run leaves evidence. - `vigilis heal` seals its whole triage-and-heal session the same way — every tool call and every decision, hash-chained in order.
- `vigilis verify ` re-walks the chain offline and reports *chain intact* or *broken at record #N*. Anyone holding the file can check it; editing or deleting any step breaks every hash after it.
When the Treeship CLI is present, heal receipts are additionally signed by an independent notary — verify with treeship verify last, or share the hosted URL. No hard dependency; --no-receipt to opt out. See docs/TREESHIP.md.
Local bundles are verifiable and auditable (they prove *what the agent did*, unaltered and in order — not that its judgment was correct); Treeship upgrades that to a signed, independently-notarized receipt.
Why I built this
I've spent my career in QA, and AI just rewrote the job: agents now write and fix tests on their own. Huge speed win — but it quietly breaks the one thing testing exists for. When an agent makes a red test green, did it *fix* the bug, or delete the test that caught it? At scale, nobody can check every change by hand.
So Vigilis isn't another self-healer — healing is becoming a commodity. It's the layer that decides honestly which failures to heal and which to refuse, and signs every call so you don't have to take its word for it.
The way I think about it: git is a ledger of your code; Vigilis is a ledger of your agent's decisions — proof you can hand to someone who doesn't already trust you.
— Piyush
How it's built
Vigilis defines its QA tools once and exposes them twice — as an MCP server and as a CLI — over one Claude agent loop:
┌──────────────────────────────┐│ core │ Anthropic Messages API + tool use │ Agent loop + Tool Registry │ browser · dom · fs · playwright · git └───────┬───────────────┬──────┘ ┌────────────▼──┐ ┌──▼───────────────┐ │ vigilis-mcp │ │ vigilis (CLI) │ │ MCP server │ │ npx vigilis ... │ │ (Claude) │ │ (used in CI) │ └───────────────┘ └──────────────────┘
The loop: Generate (explore a URL → write specs) → Triage (real-bug vs drift vs flake) → Heal (fix drift → verify green → PR, refuse real bugs). *Author* (plain-English intent → test plan) is on the roadmap.
Repo layout
vigilis/├─ packages/ │ ├─ core/ # agent loop, tool registry, Claude client, prompts, refusal actions │ ├─ mcp/ # MCP server wrapping the registry │ └─ cli/ # the vigilis command (generate | triage | heal | attest-run | verify) ├─ apps/ │ ├─ sample-shop/ # Next.js demo target (login + products + cart, with seeded drift/bug toggles) │ ├─ cloud/ # governance cloud — org audit dashboard over signed receipts │ └─ web/ # landing page → vigilis.dev └─ tests/ # generated specs land here
Develop
pnpm installcp .env.example .env # add ANTHROPIC_API_KEY pnpm build && pnpm test
Watch the full loop against the bundled demo app — see docs/DEMO.md.
Roadmap
- ✅ Generate · Triage · Heal (Playwright, Cypress & Selenium — all live-verified)
- ✅ GitHub Actions QA gate · signed provenance receipts · MCP server
- ✅ Refusal actions (Slack + Linear) · governance-cloud audit dashboard
- ✅ Zero-secret attestation:
attest-run+verify— receipts for any test run, no keys - 🚧 Author (intent → test plan) · broader agent-attestation surface
Credits
Provenance receipts are powered by [Treeship](https://www.treeship.dev) — the independent attestation primitive — and governed memory by ZMem, both built by Zerker Labs. Thanks to the Zerker Labs team for the trust primitives Vigilis stands on.
License
MIT © Piyush Pathak