Integrated Browser MCP (sheriff-stuff/vscode-integrated-browser-agent-connect) is an MCP server listed on the M8ven Trust Index. It scores 52 out of 100, grade D. It declares 18 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
D
Caution
52/100

Integrated Browser MCP

Exposes VS Code's integrated browser to external agents (Claude Code, scripts, curl) via a local HTTP API and MCP server.

→ sheriff-stuff/vscode-integrated-browser-agent-connect· 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

sheriff-stuff

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: 4 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
// tools this server exposes18 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.

browser_navigate

Navigate the target tab to a URL in the integrated VS Code browser. Replaces the current page — use browser_tab_open to keep the previous page accessible.

browser_eval

Run a JS expression in the page and return its value. Fastest way to read specific data (title, element text, form values, etc.). Prefer this over browser_dom or browser_screenshot for most read tasks. WARNING: runs arbitrary code — do not pass untrusted input.

browser_click

Click an element by CSS selector

browser_type

Type text into an element by CSS selector

browser_scroll

Scroll the page or a specific element

browser_screenshot

Capture the page as a PNG (returned as an image). Heavy — use only when visual verification matters. For reading data, browser_eval or browser_snapshot is faster. Pass fullPage:true to capture the whole scrollable page (useful for tall single-page sites or layout audits); default is viewport-only. P…

browser_emulate

Override device metrics (width, height, deviceScaleFactor, mobile, optional userAgent) on the target tab. Setting `mobile:true` also enables touch emulation so `(hover:none)` / `(pointer:coarse)` media queries fire — without that, mobile sites render their desktop fallback even at iPhone dimensions.…

browser_snapshot

Return the accessibility tree of the page. Good for understanding page structure before clicking or typing. Lighter than browser_dom.

browser_dom

Return the full outer HTML of the page. Heavy — only use when you truly need complete markup. For reading specific data, browser_eval is much faster.

browser_console

Read recent console output (last 200 per tab). Each entry has type, text, timestamp, tabId, and optional target (worker/iframe/service_worker). Omit tabId to aggregate across all tabs.

browser_network

Read recent network requests (last 200 per tab). Each entry has requestId, method, url, status, type, timestamps, tabId, and optional target. Useful for diagnosing failed API calls or missing resources. Omit tabId to aggregate.

browser_network_clear

Clear the buffered network request log

browser_url

Get the current page URL

browser_status

Check the bridge connection status

browser_tab_open

Open a new browser tab at the given URL. Returns { tabId, url, title } — the tabId is the handle for subsequent tool calls. Use this when you want to keep the current page while opening another. Requires VS Code launched with --enable-proposed-api=sheriff-stuff.integrated-browser-agent-connect.

browser_tab_close

Close a tab by id. The tab disappears from the VS Code UI.

browser_tab_list

List every tab under the bridge. Returns an array of { tabId, number, url, title, active, state, transport }. The `number` matches the "(N) " prefix shown in each tab title — if the user says "reload browser 2", find the entry with number=2 and use its tabId. `number` is null for the 21st tab and be…

browser_tab_activate

Set which tab receives tool calls that omit tabId. Note: does not move focus in the VS Code UI (the proposed API does not expose that).

// known CVEs in dependencies4 high2 low

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

high@modelcontextprotocol/sdk@1.12.1GHSA-345p-7cg4-v4c7

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

high@modelcontextprotocol/sdk@1.12.1GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.12.1GHSA-w48q-cv73-mx4w

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

highws@8.18.2GHSA-96hv-2xvq-fx4p

ws: Memory exhaustion DoS from tiny fragments and data chunks

lowws@8.18.2GHSA-58qx-3vcg-4xpx

ws: Uninitialized memory disclosure

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.
configBROWSER_BRIDGE_PORTSet the environment variable to force a specific port:
// 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

18/18 tools missing one or more hints — browser_navigate (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); browser_eval (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); browser_click (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +15 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

16/18 tool handlers declare input schemas (89%)

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

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Tool test coverage

Only 0/18 tools referenced in tests (0%)

Write tests that reference each tool by name so every tool has at least one test.

Production dependencies are patched

0 critical, 4 high severity in production deps — @modelcontextprotocol/sdk@1.12.1 (high), @modelcontextprotocol/sdk@1.12.1 (high)

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

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 6 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/sheriff-stuff/vscode-integrated-browser-agent-connect?variant=verified)](https://m8ven.ai/mcp/sheriff-stuff/vscode-integrated-browser-agent-connect)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: d7d27aa5d6e7f295a3e29600873622ef13ba0946
code hash: 52e673a6fd0d413de400d201463efc126775aa62a254044842981aa5065cc89d
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