blockwright (ThatHunky/blockwright) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 16 tools. No publisher has claimed this listing.

C
Caution
74/100

blockwright

MCP server that builds structures on a live Minecraft server over RCON: preview, build, read back, undo. No client mod, no bot.

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

ThatHunky

Source: github_repo_search

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 →

Install from

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
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 exposes16 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.

server_info

Minecraft version, player count, whether world reads/snapshots are available, and the effective blockwright configuration.

get_players

Names, worlds, block positions, look direction and gamemode of online players. Use to pick a build site near someone.

run_command

Run a raw server console command and return its output. Administrative commands (stop, op, ban, whitelist, kick, reload…) are refused unless BLOCKWRIGHT_ALLOW_ADMIN=1. Prefer the build tools; use this for things like time, weather, tp, give, say.

fill

Fill a box with one block. Modes: replace (optionally only blocks matching replace_filter), keep (only air), destroy (drop items), hollow (walls + air inside), outline (walls only, interior untouched). Splits over the 32768-block command limit automatically.

build

Place a structure described as layers of characters. palette maps one character to a block state; rows run north→south (z), characters west→east (x); y is height above origin. Space leaves the world alone. Extra single blocks go in "blocks". Rotation keeps the min corner at origin. Run with dry_run=

place_shape

Sphere, dome, cylinder, cone, pyramid, line or circle, filled or hollow. Radius r gives a diameter of 2r+1.

paste_schematic

Paste a Sponge .schem or vanilla structure .nbt. By default origin is where the schematic's min corner lands; use_offset=true adds the file's stored offset like WorldEdit //paste. ignore_air skips air so the surroundings survive.

schematic_info

Format, size, offset, DataVersion, block counts and block-entity count of a .schem/.nbt file.

schematic_write

Save a build spec or a shape as a .schem (Sponge v3) or .nbt (vanilla structure) file without touching any server. Relative paths go to the schematic dir.

preview

Render a build spec, a shape, or a schematic as ASCII layer slices (returned) and as a self-contained 3D HTML viewer (path returned; send that file to the user). Set context>0 to include the surrounding world blocks so the design is shown in place. Nothing is changed in the world.

read_region

Block counts for a box, plus ASCII layer slices when the box is small (≤4096 blocks) or full=true. Use after building to verify the result.

get_block

The block state at a position.

get_heightmap

Surface y and surface block for an x/z rectangle, as a sampled grid (rows = z north→south, columns = x west→east). The site-scouting tool: find flat ground and the y to build at (surface y + 1).

save_schematic

Copy a box from the world into a .schem (Sponge v3) or .nbt (structure) file, block entities included.

list_snapshots

Snapshots taken before writes, newest first, with ids for undo.

undo

Restore the newest snapshot(s) taken before writes (or a specific id from list_snapshots). Each restored snapshot is removed from the list.

// known CVEs in dependencies1 low

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

lowvitest@3.2.7GHSA-82fw-gwwq-j7x9

Vitest: Path Traversal / Arbitrary File Read via @vitest/mocker Redirect Mock

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// 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

16/16 tools missing one or more hints — server_info (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_players (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); run_command (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +13 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.

Destructive tools are labelled

1 tool perform destructive updates without destructiveHint — preview deletes at line 84 (fs.rm(full, { force: true }))

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

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 3 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/thathunky/blockwright?variant=verified)](https://m8ven.ai/mcp/thathunky/blockwright)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 37e2db4ffcee15262c783c89a5d4fd607d93e810
code hash: 364f435256bb848ee7962146beeb0f5f8850f6f4ad797122842fdf0da99c4d3e
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