Atlas / MCP servers / vznjs / Vx

VxBLOCK

Name: Vx
Author: vznjs

mcp/vznjs/vx

MCP server by vznjs · Audited 2026-10-10

⚑ Report / re-scan Source ↗

Verdict

BLOCK

Grade

Trust score

48 /100

Exposed tools

15 10r · 5w · 0d

Transport

stdio

License

MIT

Stars

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

The fastest task runner for JS monorepos. Measured against Turborepo and Nx, each in its own native config. vznjs.github.io/vx

Read from source at commit ea1883eda7e5OBSERVED · 2026-10-10

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code

claude mcp add vx --env API_KEY=${API_KEY} --env API_TOKEN=${API_TOKEN} --env A_KEY=${A_KEY} --env CACHE_TOKEN=${CACHE_TOKEN} -- npx -y @vzn/[email protected]

claude-desktop

{
  "mcpServers": {
    "vx": {
      "command": "npx",
      "args": [
        "-y",
        "@vzn/[email protected]"
      ],
      "env": {
        "API_KEY": "${API_KEY}",
        "API_TOKEN": "${API_TOKEN}",
        "A_KEY": "${A_KEY}",
        "CACHE_TOKEN": "${CACHE_TOKEN}"
      }
    }
  }
}

Exposed tools (15)

10 read · 5 write · 0 destructive.

Tool	Risk	Description
`checkLock`	read	The config lock audit, as
`explainCacheKey`	read	The latest cache entry recorded for a task (hash, command, exit code, duration, size).
`getCacheStats`	read	Aggregate cache statistics: entries, total bytes, and the last 24 hours of task runs and cache hits, split into hits that found outputs up to date and hits that restored them (task runs, not invocations; getRunHistory lists those).
`getConfig`	read	A resolved config as
`getFailures`	write	Why a run failed: each failed task’s exit code, its output (plain text, the first 8 KiB and last 56 KiB, secrets masked) and the files the output names (absolute, with line and column);
`getRunHistory`	read	Recent runs filtered by project / task, with per-task summary stats: p50 / p99, success and hit
`getTaskLog`	write	One task’s output in a recorded run, as
`getWorkspaceInfo`	read	The workspace doctor, the object
`listTasks`	write	Every project, its tags, and the tasks a run would see — command, dependsOn, whether it caches —
`planInit`	read	What
`planTasks`	read	What runTasks would do, without running anything:
`pruneCache`	read	Evict cache entries as
`runTasks`	write	Run tasks as
`searchDocs`	read	Search vx
`whyDidThisRerun`	write	Compare a run’s cache key for a task against the previous run and say whether it changed, what moved (

Trust audit

BLOCKgrade F · trust 48/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	FAIL
L2	Instruction surface (what it tells the agent)	PASS
L3	Class-specific surface	PASS
L4	Behavioural (sandbox)	SKIPPED

What the source does

Filesystem: declared (9 observation(s))
Network: declared (1 observation(s))
Shell: declared (4 observation(s))
Dependencies: not all pinned
Secrets in source: found

Findings (25)

HIGHFilesystem / path · fs.credential_store · CWE-22, CWE-59

packages/vx/src/orchestrator/sandbox-request.ts:633

'.netrc',

Why it matters. touches a credential store

HIGHFilesystem / path · fs.credential_store · CWE-22, CWE-59

packages/vx/src/orchestrator/sandbox-request.ts:634

'.git-credentials',

Why it matters. touches a credential store

MEDIUMHard-coded secrets · secret.db_uri · CWE-798, CWE-321

packages/vx/tests/secret-mask.test.ts:43

DATABASE_URL: 'postgres://app:pw-l11-sekret@db:5432/app',

MEDIUMHard-coded secrets · secret.generic · CWE-798, CWE-321

packages/vx/tests/cache.test.ts:559

const secret = 'AKIA-super-secret-value'

MEDIUMHard-coded secrets · secret.private_key · CWE-798, CWE-321

packages/vx-reapi/tests/wire-only-options.test.ts:22

['tlsClientKeyPem', '-----BEGIN PRIVATE KEY-----'],

LOWInventory / provenance · inv.binary · CWE-1104

packages/vx/tests/output-doc-drift.test.ts

output-doc-drift.test.ts

Why it matters. a compiled or binary member cannot be reviewed from source

Fix. ship source, or explain the binary in the README

LOWInventory / provenance · inv.binary · CWE-1104

packages/vx/tests/util-num.test.ts

util-num.test.ts

Why it matters. a compiled or binary member cannot be reviewed from source

Fix. ship source, or explain the binary in the README

LOWInventory / provenance · inv.hidden_file · CWE-1104

.oxfmtrc.json

.oxfmtrc.json

Why it matters. hidden member outside the usual dotfiles

Fix. review its purpose

LOWInventory / provenance · inv.hidden_file · CWE-1104

.oxlintrc.json

.oxlintrc.json

Why it matters. hidden member outside the usual dotfiles

Fix. review its purpose

LOWInventory / provenance · inv.hidden_file · CWE-1104

packages/vx-bench/.oxfmtrc.json

.oxfmtrc.json

Why it matters. hidden member outside the usual dotfiles

Fix. review its purpose

LOWInventory / provenance · inv.hidden_file · CWE-1104

packages/vx-bench/.oxlintrc.json

.oxlintrc.json

Why it matters. hidden member outside the usual dotfiles

Fix. review its purpose

LOWInventory / provenance · inv.hidden_file · CWE-1104

packages/vx-ci/.oxfmtrc.json

.oxfmtrc.json

Why it matters. hidden member outside the usual dotfiles

Fix. review its purpose

LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95

packages/vx-migrate/tests/nx-run-script-env.test.ts:52

await exec(

Why it matters. evaluates text as code

Fix. remove; use a parser or a dispatch table

LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95

packages/vx-migrate/tests/nx-run-script-env.test.ts:70

expect(await exec({ pregen: 'echo pre', gen: 'echo $npm_lifecycle_event' }, 'gen')).toEqual({

Why it matters. evaluates text as code

Fix. remove; use a parser or a dispatch table

LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95

packages/vx/tests/config-cache.test.ts:505

['Function', "const v = new Function('return 1')"],

Why it matters. evaluates text as code

Fix. remove; use a parser or a dispatch table

LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95

packages/vx/tests/config-eval.test.ts:1047

`export default { tasks: { build: { get exec() { throw new Error('called') } } } }\n`,

Why it matters. evaluates text as code

Fix. remove; use a parser or a dispatch table

LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95

packages/vx/tests/config-types-schema.test.ts:191

() => validateProjectConfig(exec({ persistent: X }) as never, 'p'),

Why it matters. evaluates text as code

Fix. remove; use a parser or a dispatch table

LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338

packages/vx-reapi/tests/exec-e2e.test.ts:30

return createHash('sha1').update(`blob ${bytes.byteLength}\0`).update(bytes).digest('hex')

LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338

packages/vx-reapi/tests/merkle-sweep.test.ts:249

hash: createHash('sha1').update(data).digest('hex'),

LOWFilesystem / path · fs.credential_store · CWE-22, CWE-59

packages/vx/tests/sandbox-credential-stores.unsafe.test.ts:28

['.ssh/id_ed25519', 'SSHKEY'],

Why it matters. touches a credential store

LOWFilesystem / path · fs.credential_store · CWE-22, CWE-59

packages/vx/tests/sandbox-credential-stores.unsafe.test.ts:48

'.ssh/id_ed25519',

Why it matters. touches a credential store

LOWFilesystem / path · fs.credential_store · CWE-22, CWE-59

packages/vx/tests/sandbox-credential-stores.unsafe.test.ts:62

'echo CLI > "$HOME/.aws/config"',

Why it matters. touches a credential store

LOWFilesystem / path · fs.traversal · CWE-22, CWE-59

packages/vx-bench/compare.ts:191

$schema: '../../node_modules/nx/schemas/project-schema.json',

LOWFilesystem / path · fs.traversal · CWE-22, CWE-59

packages/vx-bench/playground-spike/bench.ts:17

import { buildPlayground } from '../../vx-docs/scripts/build-playground.js'

LOWFilesystem / path · fs.traversal · CWE-22, CWE-59

packages/vx-bench/playground-spike/bench.ts:18

import { CONFIG_TEXTS, ENV, FILES } from '../../vx-docs/src/playground/fixture.js'

Gates applied: no_behavioural_pass.

Audited 2026-10-10 · audit v0.4.1 · source sha ea1883eda7e5full audit observations/trust-audit/mcp-server/vznjs__vx.json · Report an issue / request a re-scan

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

Date	Source	Verdict	Grade	Score	Change
2026-10-10	`ea1883eda7e5`	BLOCK	F	48	first audit

Questions

What tools does @vzn/vx-mcp expose?

15 in total: 10 read-only, 5 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is @vzn/vx-mcp safe to connect to an agent?

No — not without reading the findings first. The audit graded it F (48/100) and found 2 critical or high issues in the source. Each one is listed on this page with the file and line it is on.

What credentials does @vzn/vx-mcp need?

It reads API_KEY, API_TOKEN, A_KEY, CACHE_TOKEN, DEPLOY_KEY, PASSED, SECRET_KEY, VX_KEYPROP_A and VX_L26_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does @vzn/vx-mcp run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as @vzn/vx at 0.0.0.

How current is this page?

The grade is for one exact copy of the source (ea1883eda7e5), read on 2026-10-10. The repository is watched and re-audited when it changes.

Source	vznjs/vx
npm	`@vzn/vx@0.0.0`
Transports	stdio
Credentials it reads	`API_KEYAPI_TOKENA_KEYCACHE_TOKENDEPLOY_KEYPASSEDSECRET_KEYVX_KEYPROP_AVX_L26_TOKEN`
License	MIT
Activity	pushed 0d ago