jevnav MCP server

jevnav

<!-- mcp-name: io.github.dtduc-git/jevnav -->

Page truth for browser agents — and decisions that replay, test and audit.

A coding agent working on a frontend codebase gets two things from jevnav:

as facts, and diff reports font-size 32px → 28px between a mockup and the running app — the shape an agent can fix. No screenshots in the decision loop.

• Page truth, not pixels. Structure, computed styles and controls come back

probability, risky ones are gated, and the whole run is a trace that replay re-checks offline in CI: a site change that breaks a recorded decision exits 1, with no model call and no API key.

• Evidence, not confidence. Every action is a Jev decision with a calibrated

Selector-based tests break the moment a label changes, and LLM browser agents are confident, unauditable and occasionally wrong. jevnav sits in between (the longer version of this argument: docs/why.md):

into a choice question; the model answers with one element and a calibrated probability. In loop mode (jevnav go) one request also answers what to do, whether the goal is already met and which context value to type.

1. Jev picks the element. The candidate list of the current page is turned

saw them, the choice, the probability and the cost — one JSONL file per run.

1. Every decision is recorded. The trace holds the candidates as the model

destructive, goes to a human instead of clicking.

1. Risky actions are gated. p below the threshold, or an intent that looks

recorded decision against the page as it is now. A site change that breaks a target fails CI; everything else is reported as drift, not noise.

1. replay is the regression test. Offline, no model call: re-resolve every

Page truth for your agent

The facts a coding agent needs about a rendered page, without a screenshot: outline(selector) for the region's structure (tags, headings, text, boxes), styles(selector, props) for the computed values the browser resolved, page_state() for the controls jevnav can see.

Mockup vs app, as facts instead of pixels — jevnav diff reports structure and style differences and exits 1 on drift:

| element                 | property      | mockup | app  |
|---|---|---|---|
| h1 [Pricing]            | font-size     | 32px   | 28px |
| button#cta [Start free] | border-radius | 8px    | 4px  |

A font-size 32px → 28px is something an agent can fix; a red pixel diff is not. Once the app matches, pin the outcome (goal(..., success="")) and replay --execute re-checks it in CI. Full walkthrough: Matching a mockup to the app.

Install

uv tool install jevnav          # or: pip install jevnav (the MCP server is included)
playwright install chromium     # one-time browser download

Published on PyPI, listed in the MCP registry as io.github.dtduc-git/jevnav, and the replay Action is on the GitHub Marketplace.

Shortened. The full README is on GitHub.