jevbooks

← All projects

jev-webmcp-extension

sdras/jev-webmcp-extension · Homepage

Chrome extension demoing Jev × WebMCP tool selection

Agent Decisions0.83Runner-up: Classification & RoutingQuestionnaireFunnel
Automated README summary

Automatically summarized from the README on 14 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A Chrome side-panel extension that discovers WebMCP tools on the current page and predicts which tool and arguments match the user's typed input, showing confidence and latency. Built for developers exploring agent-style tool calling in the browser.

How it uses Jev

Jev answers typed questions derived from tool schemas: a Choice over tool names, Choices over enums and small integer ranges, Nouls for booleans and optional fields, and Choices over spans of the user's words for free text. Answers become { name, args, confidence, per-argument detail } used by policy.js to auto-run, confirm, or mark incomplete.

Primitives:choicescorenoul

Technique worth stealing

Convert each tool schema into typed questions (Choice/Score/Noul) so tool selection and argument filling become one parallel prediction, not text generation.

Try it

Load unpacked in chrome://extensions, paste a TypeSafe key in settings, enable on a WebMCP site.

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.13.0
Project signals
jev-1.13.0
Category
jev-1.13.0
Pattern tags
jev-1.13.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectFound in material0.89
  • Shows a System One patternFound in material0.79
  • Describes handling uncertaintynot found in the excerpt0.05
  • Reports measured numbersFound in material0.86
  • Is a runnable toolFound in material0.97
  • Top-10 learning shortlist signalnot found in the excerpt0.39
  • Is a replica of the modelnot found in the excerpt0.04
  • Solves a common problem (0–2)score on a 0–2 scale0.08 / 2
  • About JevFound in material0.98
Signals
Jev is core to the project0.89Shows a System One pattern0.79Describes handling uncertainty0.05Reports measured numbers0.86Is a runnable tool0.97Top-10 learning shortlist signal0.39Is a replica of the model0.0400.51Solves a common problem (0–2)0.08 / 2012

no-judgment band (0.40–0.60)

Design patterns
Questionnaire0.96Funnel0.80Prefetch0.62Traffic light0.27Menu0.21Check-up0.2000.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 14 Oct 2026.