minecraft-mcp@4.2.1
CAUTION· startup onlyPublisher claims: "Ask an AI about your Minecraft server and let it run it: players, worlds, configs, logs." Observed in sandbox: sends data to 127.0.0.1.
Coverage
Started and answered initialize; the tool list did not come back ( at [nodejs.internal.kHybridDispatch] (node:internal/event_target:843:20) at WebSocket.dispatchEvent (node:internal/event_target:776:26) at fireEvent (node:internal/deps/undici/undici:12111:14) Node.js v22.23.4). Authenticated tool behavior not tested.- Tested
- server startup over stdio · MCP initialize · every file read, file written and host contacted by what ran
- Not tested
- the tool list · what the tools do when called with a real credential
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
MCP_HTTP_TOKENWORLDAPI_TOKENConfiguration, not credentials: WORLDAPI_LOCAL_DIR, WORLDAPI_PLAYER, WORLDAPI_READ_ONLY, WORLDAPI_URL- Where it talks to
- no vendor host named in the codeAlso worldapi.local, modrinth.com, papermc.io — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · contacted 127.0.0.1 (undeclared)
- What we could not test
- the tool list · what the tools do when called with a real credential
Find out what these hosts are first. In the honeypot it contacted 127.0.0.1, which nothing in the package names as its own. If that is the vendor's service, fine; if you cannot place it, do not connect it.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; started and answered initialize; the tool list did not come back ( at [nodejs.internal.kHybridDispatch] (node:internal/event_target:843:20) at WebSocket.dispatchEvent (node:internal/event_target:776:26) at fireEvent (node:internal/deps/undici/undici:12111:14) Node.js v22.23.4). Authenticated tool behavior not tested) on 2026-11-11 and scored it 62/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: sends data to 127.0.0.1.
Behavior trace
Honeypot run · 30 s · 2 scenariosStatic findings
…. Name the likely causes, such as dropped items piling up, a mob farm without a kill chamber, crowds of villagers, hopper chains, or force-loaded chunks nobody needs…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.No other findings across 3,052 lines in 31 files.
Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for @mairwunnx/minecraft-mcp@4.2.1 as of 3d ago. This is the package itself, not its dependencies.
What would make this Verified
18 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
- Unclaimed publisher≈ +8 on the totalClaim mairwunnx: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.