Skills/npm/unity-mcp-cli

unity-mcp-cli@1.11.3

VERIFIED· startup only

Publisher claims: "Cross-platform CLI tool for AI Game Developer (Skills & MCP). Full AI develop and test loop. Efficient token usage, advanced tools. Creates Unity project, installs plugins, configures tools, and manages HTTP connection with Unity Editor and a game made wi" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher ivanmurzak · publishing for 248 daysInstalls 11,380Last detonated 1 h ago
$claude mcp add unity-mcp-cli -- npx -y unity-mcp-cli
WatchReport an issue

Coverage

Startup only; authenticated tool behavior not tested.
Tested
server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials

What this means for the label: Verified 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
no credential variables read in the code
Where it talks to
ai-game.dev (its own)Also nodejs.org, openupm.com, unity3d.com, unity.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
the tool list (the server exited before answering) · what the tools do when called with real credentials

Connect it under the guard. Startup only; authenticated tool behavior not tested. The code names no credential variable and talks to ai-game.dev, its own; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- npx -y unity-mcp-cli

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; startup only; authenticated tool behavior not tested) on 2026-11-15 and scored it 80/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 29 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
8.8sprocessdependency install exit 0
29sclaimedstartup only: exited (0) before answering · code: 'ERR_MODULE_NOT_FOUND', url: 'file:///tmp/ks-detonate-L9xoqG/task/home/work/acme-api/.claude/skills/unity-mcp-cli/dist/commands/bootstrap-local.js' } Node.js v22.23.5
29sprocessscript backend runs setup only
29sprocessno install scripts to re-run

Static findings

HIGH
Privileged sudo commanddist/commands/update.js:103 · Privileged sudo command — agent may execute with elevated privilegesui.info(`Try: sudo npm install -g ${PACKAGE_NAME}@latest`);Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detecteddist/commands/open.js:261 · Destructive file system command detected// Single info-level log line on dismissal — exact formatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/lib/run-tests.d.ts:49 · Process kill command — agent can terminate processes/** Kill `pid` and every process it started; true when the kill was delivered. */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagedist/commands/open.js:81 · npx invocation of non-well-known package — may execute untrusted code? `npx unity-mcp-cli ${commandName} --unity ${suggested} --path <path> --url <url>`Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiondist/commands/tools.js:41 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`\nInputs (* = required):${inputs.length === 0 ? ' none' : ''}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commanddist/lib/run-tests.js:36 · Process kill command — agent can terminate processes// Its own process group on POSIX, so the kill reaches the import workers and compilers the editor starts.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/commands/close.js:105 · Process kill command — agent can terminate processes* "kill all Unity processes on host" invocations, so a positive ID ofFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/utils/unity-hub.js:643 · Process kill command — agent can terminate processes// exceed Node's 1 MiB default, which would otherwise kill (withFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagedist/commands/open.js:82 · npx invocation of non-well-known package — may execute untrusted code: `npx unity-mcp-cli ${commandName} <path> --unity ${suggested}`;Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commanddist/commands/close.js:293 · Process kill command — agent can terminate processesspinner.error(`Failed to force-kill PID ${pid}`);Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actiondist/commands/tools.js:25 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('Details of one: unity-mcp-cli tools <name>. Call one: unity-mcp-cli run-tool <name> --input \'<json>\'.\n');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiondist/commands/tools.js:45 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`\nFull input schema:\n${JSON.stringify(tool.inputSchema, null, 2)}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packagedist/commands/open.js:69 · npx invocation of non-well-known package — may execute untrusted codeui.info(`Install it: npx unity-mcp-cli install-unity ${requestedVersion}`);Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiondist/commands/tools.js:44 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`\nCall it:\n unity-mcp-cli run-tool ${tool.name} --input '${exampleInput(tool)}'`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commanddist/lib/run-tests.js:149 · Process kill command — agent can terminate processesconst kill = async () => {Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actiondist/commands/tools.js:31 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` ${' '.repeat(width)} inputs: ${inputs.join(', ')}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packagedist/commands/update.js:67 · npx invocation of non-well-known package — may execute untrusted codeui.info('Running via npx — it always fetches the latest published version.');Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commanddist/commands/close.js:85 · Process kill command — agent can terminate processes(force ? '' : ' Or re-run with --force to hard-kill (unsaved changes are lost).');Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/lib/run-tests.js:179 · Process kill command — agent can terminate processes// An editor the kill cannot reach (stuck in the kernel) must not hold the CLI past its timeout.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/commands/close.d.ts:47 · Process kill command — agent can terminate processes* "kill all Unity processes on host" invocations, so a positive ID ofFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)dist/utils/rid.js:7 · MCP server using network transport (SSE/HTTP) — data sent over network* `gamedev-mcp-server-<rid>.zip` release asset to download. Ported from the plugin's C#Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Process kill commanddist/commands/close.js:197 · Process kill command — agent can terminate processes// With --force, still-running means the hard kill failed: no dialog explains that.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)dist/utils/rid.d.ts:5 · MCP server using network transport (SSE/HTTP) — data sent over network* `gamedev-mcp-server-<rid>.zip` release asset to download. Ported from the plugin's C#Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
npx invocation of non-well-known packagedist/lib/skill-guides.js:135 · npx invocation of non-well-known package — may execute untrusted code'- Global npm installation denied: use a user-owned Node.js installation or the npx alternative.',Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/commands/open.js:71 · npx invocation of non-well-known package — may execute untrusted codeui.info('Install latest stable: npx unity-mcp-cli install-unity');Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commanddist/commands/close.js:214 · Process kill command — agent can terminate processes.option('--force', 'Hard-kill the Editor if it does not exit within --timeout')Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈101 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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 unity-mcp-cli@1.11.3 as of 25 min ago. This is the package itself, not its dependencies.

unity-mcp-cli@1.11.3 safety verdict: Verified (startup only) — KillerSkills