xiaozhi-bridge (weemadscotsman/xiaozhi-bridge) is an MCP server listed on the M8ven Trust Index. It scores 54 out of 100, grade D. It declares 66 tools. No publisher has claimed this listing.

Caution

54/100

xiaozhi-bridge

Item: xiaozhi-bridge
Rating: 54
Author: M8ven

Connects a Xiaozhi AI voice agent to a Windows PC, enabling autonomous control via 58 MCP tools for screen vision, web browsing, file management, and system control.

→ weemadscotsman/xiaozhi-bridge · 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 push why connect →

Who stands behind it

weemadscotsman

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: 16 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 exposes60 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.

screen_capture

Screenshot the screen. Returns file path.

screen_ocr

Read text from screen using OCR.

screen_find_object

Detect objects on screen with YOLO.

screen_find_template

Find image on screen (template match).

screen_info

Get monitor sizes and positions.

mouse_click

Click at coordinates. Supports left/right/double/drag.

mouse_scroll

Scroll mouse wheel.

keyboard_type

Type text or press shortcuts (ctrl+c, alt+f4, enter, etc).

find_and_click

Find UI element by text label and click it.

window_list

List open windows.

window_focus

Focus a window by title.

window_close

Close a window by title or active window.

file_read

Read file contents.

file_write

Write content to a file.

file_list

List directory contents.

file_search

Search files by name or content.

browser_open

Open URL in browser via Playwright. Full page interaction enabled.

browser_click

Click a link, button, or element on the current page by its visible text or CSS selector.

browser_type

Type text into a form field on the page.

browser_scroll

Scroll the page up or down.

browser_get_content

Read the visible text content of the current page.

browser_screenshot

Take a screenshot of the current browser page.

browser_navigate

Navigate to URL in current tab, or go back/forward.

browser_tabs

List open browser pages.

browser_close_tab

Close a browser tab.

purpclaw_start

Start PURPCLAW AI build pipeline.

purpclaw_stop

Stop running pipeline.

purpclaw_status

Get pipeline status.

purpclaw_logs

Get pipeline logs.

git_command

Run git commands (status, log, diff, commit, push, pull).

http_request

Make HTTP requests.

clipboard

Read or write clipboard.

execute_command

Execute shell command.

open_application

Open app by name.

speak

Speak via TTS.

memory

Persistent memory (remember/recall/forget/list).

notification

Desktop toast notification.

task_schedule

Schedule background task.

task_list

List background tasks.

webcam_look

Take a photo with the PC webcam. See the room, see Ted, see what is in front of the camera.

webcam_detect

Detect people/faces/objects via webcam using YOLO.

webcam_read

Read any text visible to the webcam (signs, papers, screens) using OCR.

file_copy

Copy a file or directory.

file_move

Move or rename a file/directory.

file_delete

Delete a file or empty directory.

dir_create

Create a directory (and parents).

download_file

Download a file from a URL to local path.

process_list

List running processes. Filter by name.

process_kill

Kill a process by name or PID.

volume_control

Set system volume or mute/unmute.

zip_create

Create a zip archive from files/folder.

zip_extract

Extract a zip archive.

install_package

Install packages via pip, npm, or choco.

active_window

Get info about the currently focused window (title, process, position).

system_status

PC health check (CPU, RAM, disk, processes).

system_paths

Returns all standard Windows filesystem paths for navigation. Always call this first when user mentions Desktop, Documents, Downloads, This PC, C: drive, etc.

disk_info

Get disk space info for all drives.

network_info

Get IP addresses, WiFi status, internet connectivity.

desktop_control

Control mouse and keyboard on the PC. Move mouse, click, type text, press keys.

openclaw_gateway

Send a raw message to the OpenClaw gateway for processing by the AI agent (Socket). Use this for complex requests that need AI reasoning.

// known CVEs in dependencies16 high7 medium9 low

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

highnext@15.4.9GHSA-267c-6grr-h53f

Next.js has a Middleware / Proxy bypass in App Router applications via segment-prefetch routes

highnext@15.4.9GHSA-26hh-7cqf-hhc6

Next.js has a Middleware / Proxy bypass in App Router applications via segment-prefetch routes - Incomplete Fix Follow-Up

highnext@15.4.9GHSA-36qx-fr4f-26g5

Next.js has a Middleware / Proxy bypass in Pages Router applications using i18n

highnext@15.4.9GHSA-492v-c6pp-mqqv

Next.js has a Middleware / Proxy bypass through dynamic route parameter injection

highnext@15.4.9GHSA-5j59-xgg2-r9c4

Next has a Denial of Service with Server Components - Incomplete Fix Follow-Up

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.

configDISABLE_HMR

configMCP_BRIDGE_URLBridge HTTP server (default: http://localhost:3001)

configOPENCLAW_GATEWAYOpenClaw WebSocket (default: ws://127.0.0.1:18789)

configXIAOZHI_MCP_URLset =wss://api.xiaozhi.me/mcp/?token=YOUR_TOKEN

// 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

66/66 tools missing one or more hints — screen_capture (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); screen_ocr (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); screen_find_object (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +63 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.

License file

No license file

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

Tests exist

No test files found

Add tests that exercise each declared tool.

Production dependencies are patched

0 critical, 15 high severity in production deps — next@15.4.9 (high), next@15.4.9 (high)

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

Dev dependencies

1 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 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/weemadscotsman/xiaozhi-bridge?variant=verified)](https://m8ven.ai/mcp/weemadscotsman/xiaozhi-bridge)

Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.

commit: 754ec6ccc7c8bd05c893c9076b124c3fcebcc507

code hash: c656732af8d57fb9d89ecc6e5dc3c6ce523286f34ed7ff896c9aeb9a77fc7e42

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