WAT-AI-Broker (rozek/wat-ai-broker) is an MCP server listed on the M8ven Trust Index. It scores 56 out of 100, grade D. It declares 44 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
D
Caution
56/100

WAT-AI-Broker

Acts as a bridge between an AI assistant and a WebApp Tinkerer instance, enabling live inspection and manipulation of applets in the browser.

→ rozek/wat-ai-broker· listed on glama

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

rozek

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

Glamanot scored here

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
🚨
Known vulnerabilities in dependencies: 2 critical, 4 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
🔐
You'll be asked for 1 credential: WAT_ACCESS_TOKEN
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes44 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

connection_status
applet_info
applet_get
applet_patch

Updates one or more metadata properties of the connected applet.

applet_save

Instructs the applet to persist its current state locally ("preserve").

applet_export
applet_import
list_pages
list_widgets
find

Searches the applet for pages or widgets matching one or more criteria.

page_visit

Makes the given page the visited (i.e., shown) one.

page_get

Returns the properties of a page, excluding its widgets.

page_patch

Updates one or more properties of a page.

page_add
page_duplicate
page_delete

Destroys a page AND all widgets on it.

page_reorder

Moves a page to a new 0-based position within the page list.

widget_get

Returns all properties of a widget, including its behaviour-specific ones.

widget_patch
widget_add
widget_duplicate
widget_delete

Destroys a widget.

widget_reorder
widget_transfer

Moves a widget from one page to another, preserving all its properties.

widget_get_rect
widget_set_rect
list_behaviors
behavior_get

Returns the script source of a registered behaviour.

behavior_set
behavior_rename

Renames a registered behaviour, updating all pages/widgets that use it.

behavior_delete
behavior_usage

Lists all pages or widgets using the given behaviour.

script_get
script_set
error_report

Returns the error report of a visual (and whether it is currently broken).

configure
value_get

Returns the (observed) value of a visual.

value_set

Sets the (observed) value of a visual, triggering its reactive functions.

live_eval
overlay_open
overlay_close
dialog_open

Opens the dialog with the given name.

dialog_close

Closes the dialog with the given name.

live_screenshot

Captures the current rendered state of the connected applet as a PNG image.

// known CVEs in dependencies2 critical4 high2 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

criticalvitest@2.0.0GHSA-5xrq-8626-4rwp

When Vitest UI server is listening, arbitrary file can be read and executed

criticalvitest@2.0.0GHSA-9crc-q9x8-hgqq

Vitest allows Remote Code Execution when accessing a malicious website while Vitest API server is listening

high@modelcontextprotocol/sdk@1.12.0GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.12.0GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.12.0GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
🔐 secretWAT_ACCESS_TOKENshared secret; must match the token configured in the WebApp Tinkerer. The process exits immediately if it is unset.
configWAT_BROKER_PORTWebSocket port the WAT instance connects to (/wat)
configWAT_MCP_HOSTinterface the MCP HTTP server binds to
configWAT_MCP_PORTport the MCP client connects to (/mcp)
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

44/44 tools missing one or more hints — connection_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); applet_info (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); applet_get (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +41 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool inputs are validated

30/44 tool handlers declare input schemas (68%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Production dependencies are patched

0 critical, 4 high severity in production deps — @modelcontextprotocol/sdk@1.12.0 (high), @modelcontextprotocol/sdk@1.12.0 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dev dependencies

2 critical/high in dev-only deps (does not ship to users)

Upgrade dev dependencies when convenient.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 5 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/rozek/wat-ai-broker?variant=verified)](https://m8ven.ai/mcp/rozek/wat-ai-broker)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 23f8c97d24a1ad75bc4396ba912bc2d56bf99085
code hash: 3362dd321ccb1a7279ce8ccd03bef03c23d3e9cba6722b56689f33f2a4b4f24d
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client