Automated README summary
Automatically summarized from the README on 4 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An MCP server that lets Claude drive Firefox. Claude plans and handles ambiguous cases; Jev, a TypeSafe model returning probabilities instead of text, picks which page element to act on. Includes a benchmark against Mozilla firefox-devtools-mcp.
How it uses Jev
For each step, Jev runs one Choice over the page's interactive elements plus one Noul asking whether the goal is reached. If the Choice's confidence is below minConfidence (0.6), verification Nouls rank the top 3 candidates; the loop acts only above verifyThreshold (0.8), otherwise hands back to Claude.
Primitives:choicenoul
Technique worth stealing
Merge duplicate links to one URL before the Choice so probability is not split across equivalent options, and use absolute Nouls to verify when the relative Choice hesitates.
Try it
npm install, set TYPESAFE_API_KEY in .env, add the server to Claude Code, then run /firefox with a goal.
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-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
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 material0.93
- Shows a System One patternFound in material0.87
- Describes handling uncertaintyFound in material0.73
- Reports measured numbersunclear0.48
- Is a runnable toolFound in material0.94
- Top-10 learning shortlist signalunclear0.45
- Is a replica of the modelnot found in the excerpt0.10
- Solves a common problem (0–2)score on a 0–2 scale1.00 / 2
- About JevFound in material0.99
no-judgment band (0.40–0.60)
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 4 Nov 2026.