Look twice.Find the gem.

AI agents and MCP servers, each published with its source and what the checks found.

Marketplace

  • Everything
  • AI agents
  • Apps
  • MCP servers
  • Templates
  • What people want
  • What changed this week
  • The verification standard
  • The ooruby Index
  • Servers that publish no source
  • Reliability guides
  • What the catalogue holds
  • Sell here

Our library

  • Everything, in one place
  • Guides
  • Glossary
  • Calculators
  • Checklists and cheat sheets
  • Community

ooruby

  • Home
  • For teams
  • Site status
  • Company projects
  • RSS feed

Verification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.

AI agentsAppsMCP serversTemplatesWantedCommunityOur library
Sign inSell
Catalogue/MCP servers/Jev Browser

Jev Browser

jkudish · MCP server

Jev Browser runs a real headless browser for your agent. You give it a task and a start URL, and the Jev model chooses one action per step from the page's clickable, typeable and selectable elements, while budgets, recovery and stop gates are handled in code. You get the final page, an auditable trace of each step, console errors and a screenshot. It works as an MCP server, a command line tool or a library, and it is early software with rough edges on harder sites.

Written by ooruby from the README of @jkudish/jev-browser 0.8.5.

Not claimed by its maker. Is this yours? Prove it and answer the findings

Why it's useful

Your agent can carry out a multi-step task on a live website and show exactly which actions it took along the way.

What you could do with it

  1. 1Send it to Wikipedia with a goal such as reaching the Ristretto article, and read the final page back.
  2. 2Pull the price off a live pricing page, or get a whole guide page back as markdown.
  3. 3Review a finished run through its step trace, console errors and final screenshot.

Written from its documentation: what it says it can do, not what our checks found.

JBMCP serverResearch

Maintenance

Not measured

No release date is on record for this package yet. The nightly publisher check records one as it reaches each npm package, about once every ten nights.

Release activity only: it says nothing about quality or safety, and a finished small package can be fine without releases. How it is measured

Not yet tested
Command execution is bounded
inventory
node child_process (scripts/ensure-chromium.mjs:4)
synchronous shell execution (scripts/ensure-chromium.mjs:11)
An inventory of where the code starts another program, not a verdict on this row: whether each one runs a fixed program or whatever it is handed takes a reading by hand.

Published because it was found. A finding is information about where the limits are, not a verdict that the software is unsafe.

What this does not cover

  • ·Everything. Treat it as you would software from anywhere else.

Receipt history: every signed receipt for every version of this listing, and what changed between them.

In its maker's words

A Jev-driven browser agent: give it a task and a start URL; typed Choice actions, stop/stuck safety gates, the final page, an auditable step trace, and a screenshot. MCP server, CLI, or library.

Compare with

  • Brave Search MCP Serverside by side
  • MCP Server Atlassian Jiraside by side
  • Neurolinkside by side
Compare all 4

How far this has been checked

Static scanned

What it establishes
Its published package, or for a hosted server its source repository at a recorded commit, was read file by file, without running it, by every check in our current scan.
What it does not
How it behaves when it runs, or anything the scan does not read yet: several rubric checks, the repository's history, and compiled code in folders named dist or build. For a hosted server, that the endpoint runs the code that was read. The ooruby Index sets out exactly what was read.
Exactly what was read
Version 0.8.5, the file with digest sha512-yMqUD9bATiI5YTgoPTP0n1lE5BGvr+2BOoAg+Y0oPsb6orpwA2aqOcV79ErjvQx0i5ij17eIq5dm7ggRL4RolA==, as the registry publishes it. A published version cannot be replaced, so this names the same bytes for anyone who checks.
Authentication
Runs locally. No hosted endpoint is listed for this package. You run it on your own machine, so there is no endpoint of ours to authenticate against.
How the rungs work

Adding it

Paste this into your client's MCP configuration.

{
  "mcpServers": {
    "jev-browser": {
      "command": "npx",
      "args": [
        "-y",
        "@jkudish/jev-browser@0.8.5"
      ]
    }
  }
}

Or run it directly.

npx -y @jkudish/jev-browser@0.8.5

Pinned to 0.8.5, which is the version the findings above were found in. Drop the version to take whatever is newest, and the report on this page stops describing what you installed.

Where this came from

Registry
npm
Package
@jkudish/jev-browser
Version read
0.8.5
Resolved
2026-10-10
Open the source(opens in a new tab)

No build provenance published. The repository above is the one the publisher declared, and nothing links it to the package you would install. That is not a mark against this listing, since most packages are published this way, but it is a check nobody can run.

The badge, if this is your listing

It renders the current rung (static scanned) and links back here, where what that does and does not establish is one click away. It updates itself as the evidence deepens.

[![ooruby: static scanned](https://ooruby.com/api/badge/jkudish-jev-browser)](https://ooruby.com/market/jkudish-jev-browser)

About this listing

Kind
MCP server
Category
Research
Pricing
Free
Sandbox
No
Hosted
No
Updated
2026-10-08
Price
Free
Get it freeVisit maker
Rating
no reviews yet
0 want this so far
Sign in to vote

Sign in to watch this listing and hear when its version, rung or findings change.

More from jkudish

See the storefront
JEMCP serverDeveloper tools
Clean scanStatic scanned
Each tool returns a typed result with probabilities and, for most, a confidence score, covering claim checks, injection screening, reranking, classification, extraction and patch review. The Jev model behind them needs a provider API key.

Jev MCP

jkudish
Free

Gives your agent twelve judgement tools for verifying claims, screening content and reviewing diffs.

18.6k installs/moMIT

Similar MCP servers

All MCP servers
STMCP serverResearch
1 findingStatic scanned
One tool records each thought with its number and an estimate of how many remain, so the model can change the plan, revisit a step or test a hypothesis.

Server Sequential Thinking

modelcontextprotocol
Free

Lets your assistant reason through a problem in numbered steps, revising and branching as it goes.

484.3k installs/moSEE LICENSE IN LICENSE
DUMCP serverResearch
1 findingStatic scanned
Returns 3 results by default with snippets cut to 150 characters, and your agent can raise the limit up to 20. Content filtering can be set to strict, moderate or off, and tracking parameters are stripped from result links.

Duckduckgo MCP Server

ericthered926
Free

Lets your agent search the web and recent news through DuckDuckGo, filtered by region and time.

147.5k installs/moMIT
TAMCP serverResearch
Clean scanStatic scanned
Needs a Tavily API key, which you can supply directly or through OAuth sign-in. It runs locally or connects to Tavily's remote server, where you can set defaults such as image results, search depth and result count.

Tavily MCP

yashbtavily
Free

Lets your agent search the web, extract page content, map a website's structure and crawl sites.

117.6k installs/moMIT

Verification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.