MCP Browser (wgarrido/mcp-browser) is an MCP server listed on the M8ven Trust Index. It scores 54 out of 100, grade D. It declares 15 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
D
Caution
54/100

MCP Browser

MCP server that lets AI assistants browse the web through your real Chrome with your cookies, sessions, and fingerprint, avoiding bot detection and CAPTCHAs. Enables web browsing, content extraction, and multi-step workflows via persistent tabs.

→ wgarrido/mcp-browser· 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

wgarrido

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: 3 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.
✅
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
// tools this server exposes15 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_status

Check if the browser connection is active and return status info

close_tab

Close a persistent browser tab by its tab_id. Use this to clean up tabs opened with open_tab.

crawl

Crawl a website starting from a URL, following links up to a specified depth. Returns a list of discovered pages with titles and optional content summaries. Respects same-domain and link filter constraints.

execute_javascript

Execute arbitrary JavaScript in the context of a loaded web page. The script runs in the browser and must return a JSON-serializable value. Supports persistent sessions via tab_id — when using a tab_id, the url parameter is optional (executes on the current page).

extract_links

Extract all links from a web page. Can filter by regex pattern. Supports persistent sessions via tab_id.

fetch_page

Load a URL in the browser and return the full page content as Markdown. Supports persistent sessions via tab_id.

fetch_readable

Load a URL and extract the main article content (removes navigation, ads, sidebars). Falls back to full page content if extraction yields too little text. Supports persistent sessions via tab_id.

fetch_structured_data

Extract structured data from a web page: JSON-LD, OpenGraph tags, meta tags, tables, headings, and links. Supports persistent sessions via tab_id.

click_and_navigate

Interact with a persistent browser tab: click elements, type text, select options, submit forms, or scroll. Requires a tab_id from open_tab. Returns the page state after the action.

list_tabs

List all open browser tabs with their URLs and titles

monitor_page

Monitor a web page for content changes. Use 'start' to begin monitoring, 'check' to retrieve changes, 'stop' to end monitoring, or 'list' to see all active monitors.

multi_fetch

Fetch multiple URLs in parallel and return their content as Markdown. Useful for comparing sources or gathering information from several pages at once. Max 5 URLs.

open_tab

Open a new persistent browser tab. Returns a tab_id that can be used with other tools for multi-step workflows (login, navigation, form filling). The tab stays open until explicitly closed or the session expires.

screenshot

Take a screenshot of a web page or a specific element. Returns a PNG image. Supports persistent sessions via tab_id — when using tab_id, url is optional (screenshots the current page).

web_search

Search the web using Google or DuckDuckGo through the user's real browser. Returns structured results with title, URL, and snippet.

// known CVEs in dependencies3 high1 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

low@mozilla/readability@0.5.0GHSA-3p6v-hrg8-8qj7

@mozilla/readability Denial of Service through Regex

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.
configCACHE_ENABLEDtrue Enable in-memory page cache
configCACHE_TTL300 Cache time-to-live in seconds
configCDP_URL"": "http://localhost:9222"
configCHROME_HEADLESS"": "true"
configCHROME_PATH(auto-detect) Custom path to Chrome/Chromium executable
configCHROME_PROFILES{} JSON map of profile name → CDP URL
configDEFAULT_TIMEOUT30000 Page load timeout in ms
configLOG_LEVELinfo debug, info, warn, error
configMAX_CONCURRENT_TABS5 Max simultaneous browser tabs
configMAX_CONTENT_LENGTH50000 Max returned content in characters
configSEARCH_ENGINEgoogle google or duckduckgo
configSESSION_TIMEOUT_MINUTES30 Auto-close inactive tabs after this duration
// quality suggestions

Dependencies

12 dependencies, 1 flagged: puppeteer-core

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

15/15 tools missing one or more hints — browser_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); close_tab (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); crawl (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +12 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

13/15 tool handlers declare input schemas (87%)

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

Tool handlers catch errors

14/15 tool handlers wrap calls in try/catch (93%)

Wrap each tool handler body in try/catch and return a structured error response.

Tests exist

No test files found

Add tests that exercise each declared tool.

Production dependencies are patched

0 critical, 3 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.

Dependency freshness

1/7 production deps stale: turndown-plugin-gfm@2022-05-22 (4.1y)

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/wgarrido/mcp-browser?variant=verified)](https://m8ven.ai/mcp/wgarrido/mcp-browser)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: fe6a21f779695113ef4ae70c03c65a2aa13d44b1
code hash: 399802a1464b3962ebc84799e0b92edd79253808c32c81827f67963a88ca5071
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