Minehut MCP (Tobralla/minehut-mcp) is an MCP server listed on the M8ven Trust Index. It scores 71 out of 100, grade C. It declares 19 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
C
Caution
71/100

Minehut MCP

MCP server that lets AI agents fully manage Minehut Minecraft servers via Playwright browser automation and REST API tools, including server control, console commands, logs, and UI interactions.

→ Tobralla/minehut-mcp· 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

⚡ 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

Tobralla

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
⚠️
Tool descriptions don’t match what handlers do
1 tool describes read intent but its handler mutates — browser_screenshot (line 404: fsp.mkdir(join(homedir(), ".minehut-mcp"), { recursive: true }))
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
🔐
You'll be asked for 2 credentials: MINEHUT_PASSWORD, MINEHUT_TOKEN
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes19 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.

minehut_status

Get the status, player count, RAM, MOTD, version and plugins of a Minehut server. Accepts the server name or its id.

minehut_servers

List all servers on the logged-in Minehut account with their current status.

minehut_start

Power on a Minehut server by name or id.

minehut_stop

Power off a Minehut server by name or id.

minehut_restart

Stop and start a Minehut server again.

minehut_command

Send any console command to a Minehut server (runs with operator privileges), e.g. 'say hello', 'time set day', 'give Inxx diamond 64', 'lp user Inxx group set admin'.

minehut_logs

Read the most recent log lines of a Minehut server (useful to check console output, crashes, errors).

minehut_upgrade_ram

Change the RAM allocation of a Minehut server. Minehut limits total RAM based on your plan.

browser_open

Open a URL in the controlled browser (defaults to the Minehut dashboard) and return the page title, current URL and visible text so the AI understands the page.

browser_login_panel

Log into the Minehut dashboard in the controlled browser using the provided credentials or MINEHUT_EMAIL and MINEHUT_PASSWORD. Captures the API session automatically when possible. Cloudflare challenges may need browser_wait_manual afterward.

browser_wait_manual

Wait a number of seconds while the user finishes a manual action in the visible browser (Cloudflare challenge, 2FA, password manager), then capture the session tokens.

browser_click

Click the first visible element matching a CSS selector, e.g. 'button:has-text("Start")', '.server-row', 'a[href*="/console"]'.

browser_type

Type text into the first visible element matching a selector. Optionally press Enter afterwards.

browser_press

Press a keyboard key on the page, e.g. Enter, Escape, Tab, F5.

browser_text

Return the visible text of an element (or the whole page when no selector is given) so the AI can read the current state of the panel.

browser_screenshot

Take a screenshot of the page (or of one element) and return it as an image plus the saved file path. The AI can read the image contents.

browser_evaluate

Run a small JavaScript expression in the dashboard page and return its result. Useful for reading React state, clicking via JS, or advanced automation.

browser_close

Close the controlled browser window and release resources.

minehut_help

Show a short guide about how to use this server, including the recommended flow for first-time setup with Minehut.

// 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.
configMINEHUT_EMAIL/ MINEHUT_PASSWORD Used by browser_login_panel when credentials are not passed per call
configMINEHUT_HEADLESS0 Run the browser visibly (recommended for the first login, Cloudflare is friendlier with a visible window)
🔐 secretMINEHUT_PASSWORDMINEHUT_EMAIL / Used by browser_login_panel when credentials are not passed per call
configMINEHUT_SESSION_IDMINEHUT_TOKEN / Direct API session (captured automatically after browser login)
🔐 secretMINEHUT_TOKEN/ MINEHUT_SESSION_ID Direct API session (captured automatically after browser login)
// 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

19/19 tools missing one or more hints — minehut_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); minehut_servers (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); minehut_start (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +16 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.

Descriptions match behaviour

1 tool describes read intent but its handler mutates — browser_screenshot (line 404: fsp.mkdir(join(homedir(), ".minehut-mcp"), { recursive: true }))

Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.

Tool inputs are validated

14/17 tool handlers declare input schemas (82%)

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.).

Tests exist

No test files found

Add tests that exercise each declared tool.

Shell command execution

1 child_process/subprocess call in production code — runs shell commands (src/setup-cli.ts:8)

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Tool description accuracy

browser_screenshot: description implies read-only but handler writes/deletes/executes

Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.

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 8 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/tobralla/minehut-mcp?variant=verified)](https://m8ven.ai/mcp/tobralla/minehut-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: d6799638da15b0a9c4e317a7e728e075566b2c37
code hash: 9e369ab2c35ec201bb9f4a65a2d65b972dd8a0a9655d1b3454ac456b73e3d879
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