Judgevet

Ask TypeSafe Jev yes/no, choice and score questions and receive structured model judgments.

Connector by Alberto-Codes · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/alberto-codes-judgevet

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Ask TypeSafe Jev yes/no, choice and score questions and receive structured model judgments.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools: 4 read · 0 write · 0 deleteRead-only
Secrets: 1 (API keys, tokens or passwords)
Install scripts: None found
Runs as: Python package

Tools by what they do 4

Read from the source code; the running server may list different tools.

Read 4 · Look things up without changing anything.

ask_choice
ask_noul
ask_score
evaluate_policy

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

JEV_API__KEY

Files it touches

/etc/company/ca.pem

Tools (4)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

ask_choiceAsk a multiple-choice judgment
Ask a multiple-choice question. Takes a state (text or JSON) and an instruction, returns the ChoiceAnswer with choice name, confidence, and probabilities.
ask_noulAsk a yes/no judgment
Ask a yes/no question with a probability of true. Takes a state (text or JSON) and an instruction, returns the NoulAnswer.
ask_scoreAsk a scored judgment
Ask a scored question. Takes a state (text or JSON) and an instruction, returns the ScoreAnswer with score, confidence, legend, and probabilities. Pass criteria that match the question, for example urgency levels ending in "Critical". The default ["Poor", "Fair", "Good", "Excellent"] is a generic quality rubric.
evaluate_policyEvaluate a judgment policy
Evaluate keyed judgment questions against an acceptance policy. Questions map caller keys to noul, choice or score questions. A policy is a list of rules; each rule names a question and the answer it needs to pass. The result holds the answers, the policy result (pass or fail, with each rule's outcome and detail), the model and the usage. An unmet policy is not an error. Choice and score questions need criteria: an object of labels for choice, an ordered array lowest first for score. The ask tools' defaults do not apply here.

Signals

Stars: 0
Forks: 0
Open issues: 21
Weekly downloads: 406
Last commit: Oct 22, 2026 (6 days ago)
Last release: Oct 25, 2026 (3 days ago)
Last package publish: Oct 22, 2026 (6 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name: io.github.Alberto-Codes/judgevet
Version: 0.23.0
Auth: API key
Packages: pypi judgevet
License: MIT
Repository: github.com/Alberto-Codes/judgevet
First seen: Oct 24, 2026
Last checked: Oct 26, 2026
Source: Official MCP Registry github-graphql