Name: jevway
Author: abdallahaho

jevway MCP

Hand a browser goal to TypeSafe Jev in your Chrome or a throwaway one; get one checked summary.

Grade A Local · stdio API key 10 tools v0.5.2 MIT

No reviews yet by abdallahahonpm 1,379 Runs on your machine, nothing hosted

94/100

trust score

downloads a day

local

runs on your machine

tools declared

What it does

Hand a browser goal to TypeSafe Jev in your Chrome or a throwaway one; get one checked summary.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user jevway-mcp '--' npx -y jevway mcp

# 2 — ask your agent for something these tools do
#   jevway_inbox_create, jevway_inbox_wait, jevway_journey_start and 7 more

jevway costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

abdallahaho1 server

1 category

All 1 server

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts jevway as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.

Claude Codedeclared by this listing

This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.

claude mcp add --scope user jevway-mcp '--' npx -y jevway mcp

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.

What it asks of you

Nothing is required, but it can take TYPESAFE_API_KEY (Jev on the TypeSafe API. Set this or OPENROUTER_API_KEY.), OPENROUTER_API_KEY (Jev and the other models through OpenRouter. Set this or TYPESAFE_API_KEY.), JEVWAY_BROWSER (auto (your running Chrome), launch, launch-headless or http://host:port.) if you want to set them.

What it writes

One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.

What you approve

10 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Read from its source code. A server that builds its tool list when it starts can list more tools than this.

Parameter	Type	Required	Notes
provider	string	no	—

Parameter	Type	Required	Notes
inbox	string	yes	—
from	string	no	Part of the sender.
subject	string	no	Part of the subject.
timeout_seconds	integer	no	Default ….

Open a URL on an emulated phone and map its user journeys: each screen gets a report (type, UI patterns, ranked next taps, QA findings) and an image. Go on with jevway_journey_step (you pick) or jevway_journey_autopilot (Jev explores), describe screens with jevway_journey_annotate, end with…

Parameter	Type	Required	Notes
url	string	yes	—
device	string	no	—
intent	string	no	One journey to follow; omit to explore.
values	object	no	Text autopilot may type.
stay_within	string	no	URL prefix to stay under (default: same origin).
out_dir	string	no	Exact folder (default ./.jevway/journeys/…).

Take one step and note the screen you leave. next: an index from elements or ranked_taps ("3:2" is a dropdown option), back, restart, scroll_down, scroll_up or screen:<id>.

Parameter	Type	Required	Notes
journey	string	yes	—
next		yes	—
value	string	no	Text to type.
flow	string	no	Flow name, kept for later steps.
description	string	no	What the screen you leave is.
insight	string	no	A UX observation.

Let Jev explore: with intent until it is reached, a stop (sign-in, an irreversible tap) or no untried taps; without, for screens new screens. Skips tried, off-site and irreversible taps; returns a move log.

Parameter	Type	Required	Notes
journey	string	yes	—
screens	integer	no	—
flow	string	no	—
intent	string	no	—

Describe a screen by id, and/or move steps from_step..to_step (0-based, see journey.json) into a named flow.

Parameter	Type	Required	Notes
journey	string	yes	—
screen	string	yes	—
description	string	no	—
insight	string	no	—
relabel	object	no	—

Write journey.json and the index.html viewer, close the tab unless keep_tab, and list screens still undescribed.

Parameter	Type	Required	Notes
journey	string	yes	—
keep_tab	boolean	no	—

Parameter	Type	Required	Notes
goal	string	yes	The whole outcome, every filter and choice.
url	string	no	New session in a background tab.
tab	string	no	New session on the open tab whose URL contains this.
session	string	no	Continue this session.
values	object	no	Every text Jev may type, by key: {"city":"Lisbon"}. Nothing else is typed.
secret_keys	array	no	Keys of values that are secrets: Jev sees only the key; results show [secret:<key>].
files	object	no	Files the user asked to upload: key → absolute path or https URL.
totp	object	no	2FA on the user's own account: key → authenticator secret (base32 or otpauth URI); the current code is typed.
done_when	string	no	Visible proof of success on this call's end page; done needs it. Resend with a new goal.
checks	array	no	—
confirm_irreversible	boolean	no	—
confirm_target	string	no	The user's words naming the target ("ada/scratch"); the page must show them.
max_steps	integer	no	Default 40.
max_seconds	integer	no	Default 300.
wait_for_person_seconds	integer	no	Wait for the user at a bot check or sign-in; default 120, 0 off.
allowed_hosts	array	no	Hosts the run may be on ("github.com", "*.example.com"); leaving ends it blocked.
blocked_hosts	array	no	Hosts never to visit.
allow_coordinate_clicks	boolean	no	New session, opt-in: click a screenshot box no listed element matches (canvas).
record	boolean	no	New session: keep a video, step shots and index.html for people.
record_dir	string	no	New session: the run folder (recording on) goes here.

Read a page now, no model call, no input: url, title, page_text, the controls with their state, password fields as filled or empty. Pass one of session, tab (part of a tab's URL) or url (opened, read, closed).

Parameter	Type	Required	Notes
session	string	no	—
tab	string	no	—
url	string	no	—
pdf	boolean	no	Also save the page as a PDF; returns its path.

End a jevway_task session: forget it and close the tabs it opened, unless keep_tab. Its run folder stays.

Parameter	Type	Required	Notes
session	string	yes	—
keep_tab	boolean	no	—

Free

$0 forever

Every tool, no call limit
No card, and mcprush charges nothing for it
Source published under MIT
Runs on your machine — nothing of it reaches our gateway
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install jevway or to call it, at any volume.

ATrust score 94 / 100

Release 0.5.2 · scanned 3 Nov 2026

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score94

Findings6 threat · 1 capability

Capabilityhigh

Coveragesource

Verificationsource

Surface digest5cb0cbda91b84dd5bc26a12633a8cded8f65c47eee8fc03cb652027277653217

Score vectorthreat 100 → client 94

Term	Level	What it prices	Points
capability-exposure	high	capability blast radius (high) — client exposure if the model is manipulated	−6
verification-discount	source	publisher verification (provenance) — cryptographic build provenance ties the artifact to its source	−0
coverage-honesty	source	inspection depth (source) — how much of the target the scan could see	−0

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

Tool surfaceread

Implementation sourceread

Package metadataread

Live transportnot available

Tools were statically extracted from the published source (10 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.

Tool	Capability tags	Why the tag was assigned
jevway_inbox_create	no tags
jevway_inbox_wait	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
jevway_journey_start	no tags
jevway_journey_step	no tags
jevway_journey_autopilot	no tags
jevway_journey_annotate	no tags
jevway_journey_finish	no tags
jevway_task	no tags
jevway_look	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
jevway_end	no tags

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.

Supply chain and provenance

Integrityfirst-seen

Surface digest5cb0cbda91b84dd5

Scanned2026-11-03

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.