Atlas / MCP servers / googlechromelabs / use-webmcp-tool

use-webmcp-toolSAFE

mcp/googlechromelabs/use-webmcp-tool
Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
1 0r · 1w · 0d
Transport
—
License
Apache-2.0
Stars
195
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

A hook that registers a WebMCP tool with the browser and ties its lifecycle to a React component.

This is maintained by Chrome, and will be updated with any spec changes. The spec is 🧪 experimental, so the hook feature-detects and degrades to a no-op everywhere the API is absent.

Status / accuracy note (2026-06-05): Built against the current WebMCP spec, which exposes the imperative API on `document.modelContext` (registerTool + an AbortSignal for unregistration).

Install

npm install use-webmcp-tool

Requires React 18+ as a peer dependency. Ships as ESM with TypeScript types included — no runtime dependencies.

What it does

WebMCP lets a page expose JavaScript functions as "tools" that an AI agent (browser-built-in, iframe-hosted, or extension) can discover and call. The site author can expose functionality, and the agent uses this instead of scraping the DOM, a11y tree, or using screenshots.

The raw imperative API looks like this:

const controller = new AbortController();

document.modelContext.registerTool({
name: "add-todo",
description: "Add a new item to the user's active todo list",
inputSchema: {
type: "object",
properties: {
text: { type: "string", description: "The text content of the todo item" },
},
required: ["text"],
},
async execute({ text }) {
await addTodoItemToCollection(text);
return { content: [{ type: "text", text: `Added todo item: "${text}" successfully.` }] };
},
}, { signal: controller.signal });

// Unregister later:
controller.abort();

useWebMCP wraps that imperative, lifecycle-bound API in the declarative, lifecycle-managed model React developers already use for everything else:

import { useWebMCP } from "use-webmcp-tool";

function TodoTools({ addTodo }) {
const { supported, registered } = useWebMCP({
name: "add-todo",
description: "Add a new item to 
Read from source at commit 1aa66c3323a3OBSERVED · 2026-10-12
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add use-webmcp-tool -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "use-webmcp-tool": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}
03

Exposed tools (1)

0 read · 1 write · 0 destructive.

ToolRiskDescription
add-todowriteAdd a todo
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (1)

LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
webmcp-types, @testing-library/react, jsdom, react, react-dom, vitest
Why it matters. 6 dependency range(s) float
Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass.

Audited 2026-10-12 · audit v0.4.1 · source sha 1aa66c3323a3full audit observations/trust-audit/mcp-server/googlechromelabs__use-webmcp-tool.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-121aa66c3323a3SAFEB89first audit
06

Questions

What tools does use-webmcp-tool expose?

1 in total: 0 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is use-webmcp-tool safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does use-webmcp-tool need?

No credential environment variables were found in its source, so it appears to need none.

How current is this page?

The grade is for one exact copy of the source (1aa66c3323a3), read on 2026-10-12. The repository is watched and re-audited when it changes.

Advertisement