MCPSafe.io

Security pre-install checks for MCP servers.

Mostly safe — a couple of notes worth reading.

github · awesome-mcp-servers39b5e990fe94

Scanned 5/12/2026, 7:13:36 PM·Cached result·Fast Scan·48 rules·How we decide ↗

AIVSS Score

2.3/ 10

Low

Severity Breakdown

critical

high

medium

low

MCP Server Information

Packageawesome-mcp-servers

Version39b5e990fe94

SourceGITHUB

LicenseMIT

Publisherpunkpeye

Package age1y 5m

Stars86.8K

Downloads/wk—

Dependencies0

Homepagehttps://glama.ai/mcp/servers

Repositoryhttps://github.com/punkpeye/awesome-mcp-servers

Findings

3 of 3 findings

medium (3)

3 findings

medium (3)

AIVSS 2.3CVSS 3.5

GitHub Actions `uses:` reference is not pinned to a 40-character commit SHA. Tags (`@v4`) and branches (`@main`) are mutable — a compromised maintainer or a tag rewrite can substitute malicious code into your CI pipeline silently. Pin to a SHA: `uses: actions/checkout@8e5e7e5ab8b370d6c329ec480221332ada57f0ab`. For readability, include the version as a trailing comment: `# v4.1.1`. Tools like `pinact` / `ratchet` automate this. Allowed unpinned forms (excluded by the rule): - Local actions `.

Evidence

ref: ${{ github.event.pull_request.base.ref }}

      - name: Validate PR submission
        uses: actions/github-script@v7
        with:
          script: |
            const fs = require('fs');

Remediation

Pin every `uses:` to a 40-character commit SHA. Trailing comment with the version helps reviewers: `uses: actions/checkout@8e5e7e5ab8b370d6c329ec480221332ada57f0ab # v4.1.1` Automate the migration with `pinact` (https://github.com/suzuki-shunsuke/pinact) or `ratchet` (https://github.com/sethvargo/ratchet). Add a `pinact run --check` pre-commit hook so future PRs stay pinned. Re-pin when the action releases a new version — Dependabot can do this automatically with `version-update-strategy: inc

Report false positive →

AIVSS 2.3CVSS 3.5

Evidence

runs-on: ubuntu-latest
    steps:
      - name: Post welcome comment
        uses: actions/github-script@v7
        with:
          script: |
            const { owner, repo } = context.repo;

Remediation

Report false positive →

AIVSS 2.3CVSS 3.5

Evidence

runs-on: ubuntu-latest
    steps:
      - name: Checkout base branch
        uses: actions/checkout@v4
        with:
          ref: ${{ github.event.pull_request.base.ref }}

Remediation

Report false positive →

LLM summary— awesome-mcp-servers:39b5e990fe94

This package receives a B grade with a safety score of 90/100 but has a concerning AIVSS score of 2.2/10, indicating potential AI/LLM security weaknesses. Three medium-severity findings related to server configuration were identified, which could expose the MCP server to misuse or data leakage if not addressed before deployment. You should review and remediate these configuration issues before installing, particularly around how the server handles requests and exposes capabilities.

Signal scores

CVE check100

Static100

Publisher identity50

Permissions100

Supply chain76

Typosquat100

Package health70

Community82

Injection risks100

Secrets & exfil100

Destructive ops100

LLM judge panel

CVE check

No known CVEs found for this package or its dependencies.

Community trust

No community reports

Security policy: Not found
Advisories: 0

Scan details

Total findings: 3
Affected tools: 0 / 1
Scan type: Fast Scan
Rules run: 48
LLM consensus score: N/A
Scanned: 8h ago
Source: GITHUB

MCP Server Information

Source: GITHUB
Package: awesome-mcp-servers
Version: 39b5e990fe94
License: MIT
Publisher: punkpeye
Verified: No
Account age: 3y 10m
Added: 1y 5m ago
Homepage: https://glama.ai/mcp/servers
Repository: https://github.com/punkpeye/awesome-mcp-servers
Ecosystem: GitHub
Stars: 86.8K
Forks: 10.1K
Open issues: 1.3K
Dependencies: 0

aimcp

AIVSS Score

2.3/ 10Low

Internal score: 90/100

Severity breakdown

Scan Details

Total findings3

Affected tools0 / 1

Scanned8h ago

Scan modeFAST

SourceGITHUB

Scan IDpubfast7508eae0a4b052955278

Want deeper analysis?

Fast scan found 3 findings using rule-based analysis. Upgrade for LLM consensus across 5 judges, AI-generated remediation, and cross-file taint analysis.

View plans Scan another package

Building your own MCP server?

Run this exact engine on your private repo — before users see it on /scan.

Same rules, same LLM judges, same grade. Private scans stay isolated to your account and never appear in the public registry. Required for code your team hasn’t shipped yet.

See plans with Private scans How private scans stay private

3 of 3 findings

medium (3)

3 findings

medium (3)

AIVSS 2.3CVSS 3.5

Evidence

ref: ${{ github.event.pull_request.base.ref }}

      - name: Validate PR submission
        uses: actions/github-script@v7
        with:
          script: |
            const fs = require('fs');

Remediation

Report false positive →

AIVSS 2.3CVSS 3.5

Evidence

runs-on: ubuntu-latest
    steps:
      - name: Post welcome comment
        uses: actions/github-script@v7
        with:
          script: |
            const { owner, repo } = context.repo;

Remediation

Report false positive →

AIVSS 2.3CVSS 3.5

Evidence

runs-on: ubuntu-latest
    steps:
      - name: Checkout base branch
        uses: actions/checkout@v4
        with:
          ref: ${{ github.event.pull_request.base.ref }}

Remediation

Report false positive →

54	ref: ${{ github.event.pull_request.base.ref }}
55
56	- name: Validate PR submission
57	uses: actions/github-script@v7
58	with:
59	script: \|
60	const fs = require('fs');

16	runs-on: ubuntu-latest
17	steps:
18	- name: Post welcome comment
19	uses: actions/github-script@v7
20	with:
21	script: \|
22	const { owner, repo } = context.repo;

49	runs-on: ubuntu-latest
50	steps:
51	- name: Checkout base branch
52	uses: actions/checkout@v4
53	with:
54	ref: ${{ github.event.pull_request.base.ref }}