pinright
NPM · PINRIGHT
Version-accurate library docs for coding agents, with a supply-chain check of each dependency.
Available components
Last scanned (20 hours ago)
Scores higher than 63% of npm servers
Category Code Search and Documentation
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
- 0 of 5 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to Hiper-AI/pinright). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 17 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability60
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1682 tokens (~280/item across 6 items; 6 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 Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage99
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 96% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 7 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
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Checks we ran (15)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).
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.
- 4 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 3 Nov 26 64
First indexed and scored.
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 21 Nov 2026 · Analysed npm/pinright@1.0.0
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 | Hiper-AI/pinright |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/Hiper-AI/pinright/.github/workflows/release.yml@refs/tags/v1.0.0 |
| Rekor log index | 3675453254 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:77af8c463fd15bff94bac152ea59e3eb8e7531f7358bb8585c5d6049acf528052f7425a2dcdf8741c7a60adb53615ac919981305d81915dafb2e8fcd2 |
Background: How many MCP packages publish verified provenance →
Dependencies 5 packages
| Packages resolved | 5 |
|---|---|
| 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 →
check-manifest Audit a whole dependency tree ~285
Audits every package in a lockfile (direct and transitive) against OSV, the way Dependabot would, and says how to fix each finding: the direct upgrade on the same release line, the parent upgrade that clears a transitive one, or an override. Pass a project directory or a file path, or the file content with its name. Supported: package-lock.json, npm-shrinkwrap.json, pnpm-lock.yaml, yarn.lock, package.json, requirements.txt, poetry.lock, uv.lock, pdm.lock, pyproject.toml, Cargo.lock, Cargo.toml, go.mod, Gemfile.lock, packages.lock.json, gradle.lockfile, pom.xml, build.gradle, build.gradle.kts, libs.versions.toml, composer.lock, composer.json, requirements*.txt. Without a lockfile the tree is resolved through deps.dev. GitHub workflows (.github/workflows/*.yml, action.yml, or the directory) get an Actions check: advisories and SHA pinning.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | – | File content, when the file is not on disk yet. |
| fileName | string | – | Name of the file in content, e.g. "package-lock.json". |
| includeDev | boolean | – | Include dev dependencies (default true). |
| path | string | – | Project directory or path to a lockfile/manifest. |
No output schema declared.
No examples provided.
check-package Check a package before installing it ~177
Supply-chain verdict for one package, no docs: known advisories (CVE/GHSA, malware), deprecation, license, newest version with no known advisories, the safe version on the same release line as the one you pass, and typosquat lookalikes. For several packages use check-packages, one call for the whole list.
| Name | Type | Req | Description |
|---|---|---|---|
| detail | boolean | – | Return the full JSON report (every advisory, dates, sources) instead of the summary. |
| ecosystem | string | yes | npm, pypi, cargo, go, maven, nuget, rubygems or composer (aliases like "python" work). |
| name | string | yes | Package name as the registry knows it, e.g. "lodash", "requests". |
| version | string | – | Version you intend to install or already use. |
No output schema declared.
No examples provided.
check-packages Check a whole dependency list in one call ~128
Supply-chain verdict for up to 50 packages at once: one table row per package (verdict, version to pin, short reason) and the full notice only for the ones that need attention. Call it once with every dependency you plan to add, before writing the manifest, instead of one check per package. Packages already in the project are checked at their installed version when you omit it.
| Name | Type | Req | Description |
|---|---|---|---|
| ecosystem | string | – | Default for every package: npm, pypi, cargo, go, maven, nuget, rubygems or composer. |
| packages | array | yes | – |
No output schema declared.
No examples provided.
find-library Find a library (with security verdict) ~175
Finds the registry package for a library name ("next.js" -> npm:next, "pytorch" -> pypi:torch) and returns ids for get-docs, with the newest version that has no known advisories (safe) and a verdict. Skip it when you know the registry name: get-docs takes "npm:next" or "pypi:requests" directly, and check-packages takes plain names.
| Name | Type | Req | Description |
|---|---|---|---|
| ecosystem | string | – | npm, pypi, cargo, go, maven, nuget, rubygems or composer, when you know it. |
| libraryName | string | yes | Library name, e.g. "next.js", "requests", "tokio". |
| query | string | yes | What you want to do with it; also used to guess the language. |
No output schema declared.
No examples provided.
get-docs Documentation for the version you will use (security-checked) ~293
Returns the documentation sections that answer your question, taken from the package at a specific version (its published files and its repo at the release tag) and the project site. Without a version it documents the newest version with no known advisories. With a vulnerable version it starts with a SECURITY NOTICE and documents the safe version on the same release line, so the code you write keeps working after the upgrade.
| Name | Type | Req | Description |
|---|---|---|---|
| ecosystem | string | – | Registry, when the id does not say it or says the wrong one; overrides the id. |
| libraryId | string | – | Id from find-library, e.g. "npm:next" or "npm:next@15.1.0". A GitHub repo ("/vercel/next.js") also works. Or pass name and ecosystem instead. |
| name | string | – | Package name with ecosystem, as check-package takes them, instead of libraryId. |
| packageName | string | – | Registry package name, when it differs from the id; overrides the id. |
| query | string | – | The question or task, e.g. "protect routes with middleware". Without it: setup and main API. |
| tokens | integer | – | Approximate size of the answer in tokens (default 2500; raise it only when the answer was cut short). |
| version | string | – | Version the project uses or pins, if any. Overrides the one in libraryId. |
No output schema declared.
No examples provided.
upgrade-guide What changes between two versions ~299
Breaking changes, removed or renamed APIs, config and default changes, packages that split off, deprecations, and the advisories fixed, between the version a project uses and the one to move to. Sources: changelogs and GitHub release notes for the versions in between, migration guides when a major is crossed, and (npm) a diff of the exported .d.ts API. Call it before upgrading across a major, when a SECURITY NOTICE recommends a new major, or to fix a Dependabot PR. Without "to" it uses the version pinright recommends.
| Name | Type | Req | Description |
|---|---|---|---|
| ecosystem | string | – | npm, pypi, cargo, go, maven, nuget or rubygems. |
| from | string | – | Version the project uses now, e.g. "15.5.28" (a range like "4.x" picks its newest release). |
| libraryId | string | – | Id like "npm:next" or "pypi:langchain" (a version in it is used as "from"). |
| package | string | – | Package name, with ecosystem, instead of libraryId. |
| query | string | – | What you are changing, e.g. "middleware auth redirect"; ranks entries about it first. |
| to | string | – | Version to move to. Default: the recommended safe version. |
| tokens | integer | – | Approximate size of the answer in tokens (default 5000). |
No output schema declared.
No examples provided.
How do I install the pinright MCP server?
pinright runs locally as an npm package, launched with npx -y pinright. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · pinright
claude mcp add hiper-ai-pinright -- npx -y pinright
What is the pinright MCP server?
pinright is an MCP server listed in the public MCP registry as io.github.Hiper-AI/pinright. Version-accurate library docs for coding agents, with a supply-chain check of each dependency. This page covers its npm package (pinright).
Is the pinright MCP server safe to use?
pinright scores 79 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 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 pinright MCP server expose?
pinright exposes 6 tools: find-library, get-docs, check-package, check-packages, check-manifest, upgrade-guide. Their descriptions and schemas cost roughly 1,357 tokens of context every time the server is loaded.
Is the pinright MCP server still maintained?
pinright is still listed as active in the MCP registry. We last reached this channel on 21 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 pinright MCP server under?
pinright 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 pinright MCP server?
VerifyMCP ran 15 checks on pinright, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about pinright: Stability. One category scores 0 for that reason, because we only credit what we can confirm. 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.