Skip to content
Agentmart
Submit a tool

Jev-Style

Local 2B and 0.8B decision models: calibrated yes/no, choice and score answers for your agent.

Connector by lawrence3699 · GitHub account verified by the MCP Registry

IndexedApache-2.0Local (stdio)★ 22
Write a review

Chalk Labs

Need help deploying Jev-Style?

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/lawrence3699-jev-style

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

Local 2B and 0.8B decision models: calibrated yes/no, choice and score answers for your agent.

Use cases: model-inference, agent-orchestration

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
5 read · 0 write · 0 deleteRead-only
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Tools by what they do 5

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

Read 5 · Look things up without changing anything.

  • choice
  • decide
  • model_info
  • noul
  • score

Secrets and settings it asks for

Other settings (environment variables or headers).

  • JEV_STYLE_URL

Network hosts it talks to 4

  • amazon-massive-nlu-dataset.s3.amazonaws.com · found in code
  • github.com · found in code
  • huggingface.co · found in code
  • jevstyle.com · found in code

Files it touches

  • /home/dev
  • Your home directory (~)
  • ~/.config/jev-style/guard_config.json
  • ~/.local/state/jev-style-guard/guard.jsonl

Tools (5)

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

  • choice

    Pick the best option for the state. options: a list of option names, or {option: description or null} (1..255 options, order kept). Returns {"choice", "probabilities": {option: p}, "confidence": 0..1, ...}. confidence = (k * p_max - 1) / (k - 1) for k options: 0 = uniform, 1 = certain.

  • decide

    Ask several typed questions about one state in a single call (the state is read once). state: text, or a JSON object/array (serialised for the model). questions: {id: question}. A question is {"type": "noul", "instructions": "<statement or yes/no question>", "criteria"?: {"true": "...", "false": "..."}} {"type": "choice", "instructions": "...", "criteria": {"<option>": "<description or null>", ...}} {"type": "score", "instructions": "...", "criteria": ["<lowest level>", ..., "<highest level>"]} Score levels can also be {"label": "...", "description": "..."}. Returns the systemone-comp…

  • model_info

    Model id, context and question budgets, and which backend this MCP server uses.

  • noul

    Probability that a yes/no statement about the state is true. question: e.g. "The customer asks for a refund." or "Is the invoice overdue?" true_means / false_means: optional descriptions of what counts as true / false. Returns {"p_true": 0..1, "answer": p_true >= 0.5, ...}. Gate with your own thresholds.

  • score

    Place the state on an ordered scale. levels: 2..10 levels, lowest first; each a label or {"label": ..., "description": ...}. Returns {"score": expected level index (0 = first level, may fall between levels), "level": label of the most likely level, "legend": {index: label}, "probabilities": {index: p}, "confidence", ...}.

Signals

Stars
22
Forks
2
Open issues
0
Contributors
2
Weekly downloads
402
Last commit
Oct 17, 2026 (14 days ago)
Last release
Oct 17, 2026 (14 days ago)
Last package publish
Oct 17, 2026 (14 days ago)

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

Details

Registry name
io.github.lawrence3699/jev-style
Version
0.5.0
Auth
No auth
Packages
pypi jev-style
License
Apache-2.0
Repository
github.com/lawrence3699/jev-style
Website
jevstyle.com
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql

More from lawrence3699

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 Jev-Style 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 Jev-Style?

CallGet help
Cite this page

Jev-Style MCP server. Agent Mart. https://agentmart.dev/connectors/lawrence3699-jev-style (last updated 2026-10-24)