Mmcp.market

Safeinstall MCP server

by Mickdownunder·io.github.Mickdownunder/safeinstall·v0.12.0

Local-first supply-chain security gate for npm/pnpm/bun: typosquat, release age, provenance checks

A92/100grade A
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

3 stars67 downloads/wk

Reviews

Write one

Nobody has reviewed Safeinstall yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Safeinstall tools (1)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • check_package

    Check whether installing an npm package would be blocked by SafeInstall's

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan41 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 9 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the Safeinstall repository's README, as published. We do not edit it. Read it on GitHub

SafeInstall Supply-chain security for the AI-agent era.

The install gate for npm, pnpm, and bun — for the humans who type install, the AI agents that run it for them, and the config that programs those agents. Policy runs first. Then your package manager. Not the other way around. Local-first · No cloud · No account · MIT · Free forever

What it does

SafeInstall runs your policy before your package manager — locally, blocking by default. One tool, three layers of defense:

  • 🧑‍💻 For the humans who install — prefix any command: safeinstall pnpm add axios. Policy runs, then pnpm. Release age, install scripts, untrusted sources, typo-squats, and cryptographic provenance are checked before anything touches disk.
  • 🤖 For the AI agents that install for you — an MCP tool agents can call, plus a shell guard that intercepts install commands in Claude Code, Codex, and Cursor before they run. Best-effort shell interception — one defense layer that fires even when the agent isn't cooperating, not a lossless guarantee.
  • 🔒 For the files that program the agents — the Agent Trust Surface: a committed hash baseline of your config, hooks, rules, and MCP files, reconciled locally and re-verified in CI, so tampering with the rules surfaces as drift instead of silently owning every future session — with a fully consistent rewrite caught by human review of the diff, not the automated check alone.

Why SafeInstall

AI coding tools suggest packages in seconds. They don't check publish dates. They don't read install scripts. They don't verify the source. You type "yes" and move on.

SafeInstall is the gate between suggestion and execution.

$ safeinstall pnpm add compromised-pkg@9.9.9

Install blocked.
- compromised-pkg@9.9.9
  Blocked: release too new (published 3 hours ago; minimum is 72 hours).
  Blocked: install script present (has postinstall).

No dashboard. No account. No cloud. One command prefix — policy runs locally, blocks by default, then invokes the real tool.

Catching a maintainer-compromise attack

A valid Sigstore signature is not enough. An attacker who compromises an npm maintainer account can publish a malicious version of a package you already trust, and the attestation on that malicious version will cryptographically verify — signed by a GitHub Actions workflow the attacker controls in a fork of the real repository.

SafeInstall catches this. Pin the expected source repository with provenance.trustedPublishers and any build that comes from anywhere else is blocked, even if the signature is valid:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Install directly

Runs npx -y safeinstall-cli on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add safeinstall -- npx -y safeinstall-cli
Add to Cursor

Safeinstall: common questions

Is Safeinstall MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Safeinstall safety report
How do I install Safeinstall?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does Safeinstall need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Safeinstall maintained?
The last commit was 9 days ago (2026-09-17). The latest release is v0.12.0.
What can I use instead of Safeinstall?
Servers from other publishers that do the same job: Reversecore MCP server, CodeInspectus MCP server and MCPProxy MCP server. Compare all Safeinstall alternatives.

Alternatives to Safeinstall

Same job from other publishers: the closest match first, then the best rated.

All Safeinstall alternatives →
  • Reversecore MCP
    Security-first MCP server for reverse engineering, malware analysis, forensics, and SAST.
    B
  • CodeInspectus
    Local-first MCP security scanner and CLI for AI-generated applications.
    C
  • MCPProxy
    Local-first MCP proxy with BM25 tool discovery, security scanning, quarantine & ~99% token savings
    B
  • Npm Sentinel
    Advanced NPM analysis: Recursive security scanning, ecosystem awareness, and deep insights.
    A
  • Prodcheck
    4,372 pre-production checks: security, performance, scale, integrations, post-launch.
    A

More from Mickdownunder →