Spec Driven Development
by formulahendry
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Runs on your computer★ 440MITUpdated 14 months ago
Install
Judgevet
Overview
Description from the maker (original English)
Ask TypeSafe Jev yes/no, choice and score questions and receive structured model judgments.
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
- UsageiNot measured yet★ –
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: JEV_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:
JEV_API__KEY
Values marked secret are keys to your account. Never share them or paste them into a chat.
You need
- PyPIPython’s uv installed (for the uvx 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": {
"judgevet": {
"command": "uvx",
"args": [
"judgevet"
],
"env": {
"JEV_API__KEY": "your-value"
}
}
}
}Run this in your terminal
claude mcp add judgevet --env JEV_API__KEY=your-value -- uvx judgevetFill 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": {
"judgevet": {
"command": "uvx",
"args": [
"judgevet"
],
"env": {
"JEV_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": {
"judgevet": {
"type": "stdio",
"command": "uvx",
"args": [
"judgevet"
],
"env": {
"JEV_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
- TypeSafe API key. Tool inputs are sent to TypeSafe for judgment.
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 7, 2026
- ✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account Alberto-Codes, 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 18348 servers in this category
- Published to the registry more recently than 75% of the other 18348 servers in this category
- Basic checks equal to or better than 100% of the other 18348 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 Judgevet 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: JEV_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 (0.23.0) reached the registry 13 days ago.
Which apps can use it?
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.
What can I use instead?
In the same category: Spec Driven Development, Remote Desktop Commander, 好縮 Short
Alternatives
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
Remote Desktop Commander
by desktop-commander
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Runs in the cloud★ 211Updated 2 days ago
Install
好縮 Short
by gooonamee
Smart URL shortener: create, tag and track short links on s.gooo.name.
Runs in the cloudUpdated today
Install
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.
judgevet
A typed Python client for TypeSafe's Jev (System One) judgment model, with CLI and optional MCP entry points. Use it to ask structured questions about content—for example, whether a support ticket concerns billing.
The state is your content. A question describes what to evaluate. A typed answer contains the model's values, which your application can inspect or compare with a local acceptance policy.
Unofficial and not affiliated with TypeSafe. The official TypeSafe Python SDK also provides typed questions and synchronous and asynchronous clients. judgevet adds a shared library, CLI and MCP contract with local policy evaluation. The library and CLI install without the MCP runtime.
Documentation status: draft. Start below or follow the first-judgment tutorial for environment setup, checkpoints and recovery steps.
Install and ask one question
Use Python 3.12 or newer. In a virtual environment:
python -m pip install 'judgevet==0.23.0'judgevet --help
<!-- x-release-please-end -->Supply a TypeSafe API key through your process environment or secret provider. This example reads JEV_API__KEY and passes it explicitly to the library. Do not put real keys in source or command arguments. The installation guide covers other installation methods.
This call sends the state, questions and selected model to the configured service. Send only content you are authorized to disclose. Read the data and credential guidance before using sensitive content. The example uses a synthetic ticket:
import osfrom judgevet import HTTPSystemOneAdapter, Noul
with HTTPSystemOneAdapter(api_key=os.environ["JEV_API__KEY"]) as client: response = client.system_one( state="I was charged twice. Please help today.", questions={"billing": Noul(instructions="Is this about billing?")}, )
answer = response.nouls["billing"] print(f"Probability of billing: {answer.noul}") print(f"Resolved model: {response.model}") print(f"Input tokens: {response.usage.input_tokens}")
The context manager closes the HTTP client after the call. The answer remains available. If the import or call fails, use the tutorial's recovery steps or the troubleshooting guide.
Read the answer and make a decision
A Noul value such as 0.85 reports the model's probability of yes. The actual value varies. It is not a boolean, a measured accuracy rate or an instruction to route the ticket. Noul has no separate confidence field. See the vendor's Noul definition.
The returned container also records the resolved model and token usage. Other question types let you select a label or evaluate an ordered rubric:
| Question | What its answer contains |
|---|---|
Noul | Probability of yes |
Choice | Selected label, per-label probabilities and confidence |
Score | Continuous score, rubric legend, per-level probabilities and confidence |
The vendor API reference defines those fields. The question-type explanation shows how to choose a type and distinguish score, confidence and probability.
A local policy can require a minimum value before your application accepts an answer. For example, 0.85 meets a minimum of 0.8 and fails one of 0.9. These are teaching thresholds, not production recommendations. A passing policy does not prove the model is correct or perform the application's next action. Try the first-policy tutorial with synthetic answers; it requires no key or network.
Choose your next task
| Need | Start here |
|---|---|
| Learn one complete service call | First judgment |
| Call from an async application | Async Python guide |
| Use a mounted key or secret provider | Credential sources |
| Deploy in containers or serverless | Deployment guide |
| Correlate diagnostic events | Event contract and caller binding |
| Configure a proxy or private CA | Network configuration |
| Configure bounded retries | Retry limits |
| Handle service and transport failures | Library error handling |
| Evaluate typed or JSON policies in Python | Policy guide |
| Use shell commands, files or stdin | CLI inputs and CLI policies |
| Give an agent judgment tools | Optional MCP installation, connection and discovery |
| Look up types, options or schemas | Reference map |
| Understand thresholds and tradeoffs | Local policy explanation |
| Choose an entry point and own its lifecycle | Library-first architecture |
The CLI uses the same library and can return JSON or a policy exit status. The optional MCP server exposes ask_noul, ask_choice, ask_score and evaluate_policy over stdio. Follow the connection guide to install the extra and configure a host. These are alternative entry points; you do not need MCP to use Python or the CLI.
Know the limits
Exact documentation examples run against isolated installations with synthetic answers. Those checks establish local wiring, not model quality or calibration. Live evidence covers only the observed cases and resolved jev-1.13.0 model. The 429/529 error bodies remain unseen; other models and untouched fields remain unverified. The verification explanation separates local tests, vendor statements and live observations.
Diagnostics are quiet by default. Debug metadata excludes state and question text, but protocol errors, CLI error envelopes and arbitrary tracebacks can contain sensitive content. Review them before sharing. The security policy describes credential, disclosure and diagnostic limits.
Maintainers
Read the contribution policy before proposing work. Use the maintainer procedures for documentation checks, package verification and releases. Repository contribution rules define gates and commits. The verification ledger records which service claims a live call has verified.