Skip to content
Agentmart
Submit a tool

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)
Write a review

Chalk Labs

Need help deploying Judgevet?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

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.

We use your email only for this newsletter. Privacy

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

Network hosts it talks to 21

  • alberto-codes.github.io · found in code
  • api.typesafe.ai · found in code
  • arxiv.org · found in code
  • cheatsheetseries.owasp.org · found in code
  • cisa.gov · found in code
  • code.claude.com · found in code
  • cyclonedx.org · found in code
  • docs.astral.sh · found in code
  • docs.aws.amazon.com · found in code
  • docs.cloud.google.com · found in code
  • docs.litellm.ai · found in code
  • docs.ollama.com · found in code
  • docs.typesafe.ai · found in code
  • github.com · found in code
  • google.aip.dev · found in code
  • jsonlines.org · found in code
  • man7.org · found in code
  • nvlpubs.nist.gov · found in code
  • opentelemetry.io · found in code
  • pydantic.dev · found in code
  • raw.githubusercontent.com · found in code

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 (8 days ago)
Last release
Oct 25, 2026 (5 days ago)
Last package publish
Oct 22, 2026 (8 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 Registrygithub-graphql

More from Alberto-Codes

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get Judgevet running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying Judgevet?

CallGet help
Cite this page

Judgevet MCP server. Agent Mart. https://agentmart.dev/connectors/alberto-codes-judgevet (last updated 2026-10-26)