Name: pinright
Author: hiper-ai

pinright MCP

Version-accurate library docs for coding agents, with a supply-chain check of each dependency.

Grade B Local · stdio No auth needed 6 tools v1.0.0 MIT

No reviews yet by hiper-ainpm 571 Runs on your machine, nothing hosted

88/100

trust score

downloads a day

local

runs on your machine

571

downloads in 30d

What it does

Version-accurate library docs for coding agents, with a supply-chain check of each dependency.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user pinright-mcp '--' npx -y pinright

# 2 — ask your agent for something these tools do
#   find-library, get-docs, check-package and 3 more

pinright costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

hiper-ai1 server

1 category

All 1 server

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts pinright as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.

Claude Codedeclared by this listing

This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.

claude mcp add --scope user pinright-mcp '--' npx -y pinright

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.

What it asks of you

Nothing is required, but it can take GITHUB_TOKEN (Optional. Raises the GitHub API limit from 60 to 5,000 requests an hour (monorepo docs, upgrade guides). Read-only use.), PINRIGHT_GH_CLI (Optional. 1 uses the GitHub CLI login (gh auth token) when GITHUB_TOKEN is not set.) if you want to set them.

What it writes

One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.

What you approve

6 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Read from its source code. A server that builds its tool list when it starts can list more tools than this.

Finds the registry package for a library name ("next.js" -> npm:next, "pytorch" -> pypi:torch) and returns

Parameter	Type	Required	Notes
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.
ecosystem	string	no	npm, pypi, cargo, go, maven, nuget, rubygems or composer, when you know it.

Returns the documentation sections that answer your question, taken from the package at a specific version

Parameter	Type	Required	Notes
libraryId	string	yes	Id from find-library, e.g. "npm:next" or "npm:next@15.1.0". A GitHub repo ("/vercel/next.js") also works.
query	string	yes	The question or task, e.g. "protect routes with middleware".
version	string	no	Version the project uses or pins, if any. Overrides the one in libraryId.
tokens	integer	no	Approximate size of the answer in tokens (default 2500; raise it only when the answer was cut short).
ecosystem	string	no	Registry, when the id does not say it or says the wrong one; overrides the id.
packageName	string	no	Registry package name, when it differs from the id; overrides the id.

Supply-chain verdict for one package, no docs: known advisories (CVE/GHSA, malware), deprecation, license,

Parameter	Type	Required	Notes
name	string	yes	Package name as the registry knows it, e.g. "lodash", "requests".
ecosystem	string	yes	npm, pypi, cargo, go, maven, nuget, rubygems or composer (aliases like "python" work).
version	string	no	Version you intend to install or already use.
detail	boolean	no	Return the full JSON report (every advisory, dates, sources) instead of the summary.

Supply-chain verdict for up to … packages at once: one table row per package (verdict, version to pin,

Parameter	Type	Required	Notes
packages	array	yes	—
ecosystem	string	no	Default for every package: npm, pypi, cargo, go, maven, nuget, rubygems or composer.

Audits every package in a lockfile (direct and transitive) against OSV, the way Dependabot would, and says

Parameter	Type	Required	Notes
path	string	no	Project directory or path to a lockfile/manifest.
content	string	no	File content, when the file is not on disk yet.
fileName	string	no	Name of the file in content, e.g. "package-lock.json".
includeDev	boolean	no	Include dev dependencies (default true).

Breaking changes, removed or renamed APIs, config and default changes, packages that split off, deprecations,

Parameter	Type	Required	Notes
libraryId	string	no	Id like "npm:next" or "pypi:langchain" (a version in it is used as "from").
package	string	no	Package name, with ecosystem, instead of libraryId.
ecosystem	string	no	npm, pypi, cargo, go, maven, nuget or rubygems.
from	string	no	Version the project uses now, e.g. "15.5.28" (a range like "4.x" picks its newest release).
to	string	no	Version to move to. Default: the recommended safe version.
query	string	no	What you are changing, e.g. "middleware auth redirect"; ranks entries about it first.
tokens	integer	no	Approximate size of the answer in tokens (default 5000).

Free

$0 forever

Every tool, no call limit
No card, and mcprush charges nothing for it
Source published under MIT
Runs on your machine — nothing of it reaches our gateway
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install pinright or to call it, at any volume.

BTrust score 88 / 100

Release 1.0.0 · scanned 4 Nov 2026

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score94

Client score88

Findings6 threat · 0 capability

Capabilityhigh

Coveragesource

Verificationsource

Surface digestd0b88b483fe59ca32d5e98f74bc0ed5e4a3831201d21f23122ea6549939764ca

Score vectorthreat 94 → client 88

Term	Level	What it prices	Points
capability-exposure	high	capability blast radius (high) — client exposure if the model is manipulated	−6
verification-discount	source	publisher verification (provenance) — cryptographic build provenance ties the artifact to its source	−0
coverage-honesty	source	inspection depth (source) — how much of the target the scan could see	−0

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

Tool surfaceread

Implementation sourceread

Package metadataread

Live transportnot available

Tools were statically extracted from the published source (6 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".

2 of the 6 recovered tools are registered only when docsOnlyAblation() holds (dist/mcp.js:183) — typically when a key or option is configured. They are part of the server's surface and were analysed; the other branch of the same condition registers the rest.

4 of the 6 recovered tools are registered only when docsOnlyAblation() is false (dist/mcp.js:183) — typically when a key or option is configured. They are part of the server's surface and were analysed; the other branch of the same condition registers the rest.

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.

No tool is registered unconditionally · (1) 2 only when docsOnlyAblation() holds (dist/mcp.js:183) · (2) 4 only when docsOnlyAblation() is false (dist/mcp.js:183) — typically when a key or option is configured. All 6 are in the table below and were analysed; the conditional ones are marked.

Tool	Capability tags	Why the tag was assigned
find-library conditional (1)	no tags
get-docs conditional (1)	no tags
check-package conditional (2)	no tags
check-packages conditional (2)	no tags
check-manifest conditional (2)	no tags
upgrade-guide conditional (2)	no tags

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.

Supply chain and provenance

Integrityfirst-seen

Surface digestd0b88b483fe59ca3

Scanned2026-11-04

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.