npx-vibe
NPM · NPX-VIBE
Read-only npm package and project dependency preflight tools for AI applications.
Available components
Last scanned (8 hours ago)
Scores higher than 98% of npm servers
Category Security
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to Devrajsinh-Jhala/NPM-Vibe-check). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 34 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability73
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 680 tokens (~170/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (16)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 3 Nov 26 +4
- Stability: fail → pass ▲ security
- 30 Oct 26 0
- Package version: 1.5.1 → 3.0.0 functional
- 28 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 63 to 67.
- 27 Oct 26 −1
No change was recorded against any check on this day. Stability & Change Management went from 67 to 63.
- 21 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 63 to 67.
- 20 Oct 26 −1
No change was recorded against any check on this day. Stability & Change Management went from 67 to 63.
- 17 Oct 26 +3
No change was recorded against any check on this day. Stability & Change Management went from 50 to 67.
- 15 Oct 26 −3
No change was recorded against any check on this day. Stability & Change Management went from 67 to 47.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed npm/npx-vibe@3.0.0
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | Devrajsinh-Jhala/NPM-Vibe-check |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/Devrajsinh-Jhala/NPM-Vibe-check/.github/workflows/release.yml@refs/tags/v3.0.0 |
| Rekor log index | 3051513054 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:b5fa7a43f58f172c35e92768a4b028fb8b8c31ada97a37aa863f26576521f51a393e3e6ed576682c683b55aeaafb8e081f09c3905c71889da70f70417 |
Background: How many MCP packages publish verified provenance →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
approve_scripts Decide npm install-script permissions ~174
Review every dependency npm would allow to run an install script, and return approve, review, or deny for each with the source evidence behind it. Reads package-lock.json and never executes a script. Use when npm reports pending allowScripts entries or after a lockfile change adds one.
| Name | Type | Req | Description |
|---|---|---|---|
| ai | string | – | Optional AI review mode. Heuristic-only scanning is the default. |
| all | boolean | – | Re-review packages already recorded in allowScripts. |
| concurrency | integer | – | Maximum concurrent package reviews. |
| model | string | – | Exact provider model identifier, required for online review. Ollama may use its configured local model. No online model catalog is bundled. |
| path | string | – | Project directory or package.json path. |
| provider | string | – | AI provider. Credentials are read from environment variables, never tool arguments. |
| Name | Type | Req | Description |
|---|---|---|---|
| coverage | object | yes | – |
| decision | object | yes | – |
| error | object | – | – |
| kind | string | yes | – |
| report | object | – | – |
| schemaVersion | integer | yes | – |
| status | string | yes | – |
| subject | object | – | – |
| tool | object | yes | – |
No examples provided.
list_providers List supported AI providers ~63
Return the AI providers npx-vibe can call, the environment variable each reads its key from, and where that provider publishes its current model list. No model catalog is bundled, so a model must be named explicitly. This does not access a provider or require credentials.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| providers | array | yes | – |
| schemaVersion | integer | yes | – |
| tool | object | yes | – |
No examples provided.
scan_package Scan an npm package ~144
Resolve, verify, and inspect one public npm registry package without executing package code. Use before installing, recommending, or running an unfamiliar package. Obey decision.action: continue, review, stop, or retry.
| Name | Type | Req | Description |
|---|---|---|---|
| ai | string | – | Optional AI review mode. Heuristic-only scanning is the default. |
| model | string | – | Exact provider model identifier, required for online review. Ollama may use its configured local model. No online model catalog is bundled. |
| package | string | yes | npm package spec such as esbuild, @scope/tool, or package@version. |
| provider | string | – | AI provider. Credentials are read from environment variables, never tool arguments. |
| Name | Type | Req | Description |
|---|---|---|---|
| coverage | object | yes | – |
| decision | object | yes | – |
| error | object | – | – |
| kind | string | yes | – |
| report | object | – | – |
| schemaVersion | integer | yes | – |
| status | string | yes | – |
| subject | object | – | – |
| tool | object | yes | – |
No examples provided.
scan_project Scan project dependencies ~247
Inspect registry dependencies without installing or executing them. Default tree reviews require an npm lockfile packages map; directOnly explicitly narrows scope. Skipped packages or limits make coverage incomplete: retry, never continue. Use after dependency or lockfile changes and before installation.
| Name | Type | Req | Description |
|---|---|---|---|
| ai | string | – | Optional AI review mode. Heuristic-only scanning is the default. |
| aiLimit | integer | – | Maximum triggered AI reviews when AI is explicitly enabled. |
| concurrency | integer | – | Maximum concurrent heuristic package scans. |
| directOnly | boolean | – | Scan only the direct dependencies named in package.json. By default every registry-resolved package in package-lock.json is scanned. |
| includeDev | boolean | – | Include devDependencies in addition to production and optional dependencies. |
| maxPackages | integer | – | Maximum packages scanned in one project scan. |
| model | string | – | Exact provider model identifier, required for online review. Ollama may use its configured local model. No online model catalog is bundled. |
| path | string | – | Project directory or package.json path, relative to the MCP server working directory or absolute. |
| provider | string | – | AI provider. Credentials are read from environment variables, never tool arguments. |
| Name | Type | Req | Description |
|---|---|---|---|
| coverage | object | yes | – |
| decision | object | yes | – |
| error | object | – | – |
| kind | string | yes | – |
| report | object | – | – |
| schemaVersion | integer | yes | – |
| status | string | yes | – |
| subject | object | – | – |
| tool | object | yes | – |
No examples provided.
How do I install the npx-vibe MCP server?
npx-vibe runs locally as an npm package, launched with npx -y npx-vibe --mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
npm · npx-vibe
claude mcp add devrajsinh-jhala-npx-vibe -- npx -y npx-vibe --mcp
What is the npx-vibe MCP server?
npx-vibe is an MCP server listed in the public MCP registry as io.github.Devrajsinh-Jhala/npx-vibe. Read-only npm package and project dependency preflight tools for AI applications. This page covers its npm package (npx-vibe).
Is the npx-vibe MCP server safe to use?
npx-vibe scores 95 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the npx-vibe MCP server expose?
npx-vibe exposes 4 tools: scan_package, scan_project, approve_scripts, list_providers. Their descriptions and schemas cost roughly 628 tokens of context every time the server is loaded.
Is the npx-vibe MCP server still maintained?
npx-vibe is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the npx-vibe MCP server under?
npx-vibe declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the npx-vibe MCP server?
VerifyMCP ran 16 checks on npx-vibe, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.