MCP.Market

mcp-scan MCP server

by CodingSelim·io.github.CodingSelim/mcp-scan·v0.2.1
No reviews yet

Passive security scanner: audits MCP servers against the OWASP MCP Top 10, graded A-F.

A88/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
New

0 stars38 downloads/wk

Reviews

Write one

Nobody has reviewed mcp-scan yet.

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

mcp-scan tools (2)

write = sends, deletes, buys or posts

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

  • list_checks

    List the security checks mcp-scan runs and their OWASP MCP Top 10 mapping. Takes no arguments.

  • scan_mcp_server

    Audit a Model Context Protocol server against the OWASP MCP Top 10 and return a graded (A-F) security report. Pass a stdio target ('command' plus optional 'args'/'env') OR a remote 'url' (with optional 'headers'). Passive: it enumerates the server's advertised tools/prompts/resources and analyzes them statically, never invoking tools. Scanning a stdio target spawns that command, so only scan serve

Public scan report

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

no findings
  • Code scan57 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 56 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How mcp-scan compares

Against every graded Security MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
88/100
higher than 85% of 915 Security servers
Tools
2
the typical Security server has 6
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
38
more than 28% of 248 Security servers with a package

What its tools let an agent do: 2 read

Install mcp-scan in Claude Code, Cursor or VS Code

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

claude mcp add mcp-scan -- npx -y owasp-mcp-scan
Add to Cursor

What the publisher says

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

🛡️ mcp-scan

Passive security scanner for Model Context Protocol servers. Point it at any running MCP server; it audits the live server against the OWASP MCP Top 10 and grades it A–F. Read-only, so it is safe to run against production.

npx owasp-mcp-scan --stdio "npx -y @modelcontextprotocol/server-filesystem /tmp"

I ran it against the 12 most-installed MCP servers. 9 of them failed. No install, no config, no exploiting anything.

Why

MCP tool descriptions are fed straight into your model's context, and most public servers were never security-reviewed. A bad one can hide instructions in a description, expose a raw-shell tool, or leak a key; and your agent acts on it. Endor Labs found 82% of servers prone to path traversal, 34% to command injection.

mcp-scan is the gut-check before you wire a server in. It's passive: it reads advertised capabilities and analyzes them statically, never invoking tools, so it's safe against production servers.

How it works

  1. Connects to the server over stdio or Streamable HTTP and enumerates every advertised tool, prompt, and resource.
  2. Runs 12 static checks across that surface: secrets, injection, SSRF, path traversal, tool poisoning, excessive scope, and more.
  3. toxic-flow reasons across the whole toolset for the lethal trifecta (reads private data + ingests untrusted content + can exfiltrate), the shape single-tool scanners miss.
  4. Scores 0-100 and grades A-F (any critical forces F). Emits console, JSON, or SARIF.

It never calls a tool, never fuzzes, and never sends an exploit. The worst it does is read what the server already tells everyone.

Real findings on real servers

12 popular npm servers, actual output (snapshot 2026-07-11, full benchmark):

9 of 12 flagged, 3 clean, every row audited finding-by-finding, false positives stripped rather than padded. Reproduce any row yourself:

npx owasp-mcp-scan --stdio "npx -y firecrawl-mcp"     # F: lethal trifecta + code exec
npx owasp-mcp-scan --stdio "npx -y @modelcontextprotocol/server-everything"   # A: clean

Use it

CLI

Shortened. The full README is on GitHub.

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

mcp-scan: common questions

Is mcp-scan MCP server safe?
Yes, by our scan: it is graded A (88/100). Read the mcp-scan safety report
How do I install mcp-scan?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does mcp-scan need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is mcp-scan maintained?
The last commit was 95 days ago (2026-08-01). The latest release is v0.2.1.
What can I use instead of mcp-scan?
Servers from other publishers that do the same job: Solana Security Standard MCP server, APSA mobile app security audit MCP server and Security Suite MCP server.
How does mcp-scan compare with other Security MCP servers?
safety score 88/100 (higher than 85% of 915 Security servers); tools 2 (the typical Security server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to mcp-scan

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

  • Solana Security Standard
    Scan Solana/Anchor code against the Solana Security Standard and serve the ruleset to MCP clients.
    A
  • APSA mobile app security audit
    Local, evidence-graded Android/iOS security audits of source, APK, AAB and IPA for AI agents.
    A
  • Security Suite
    Every GuardBee MCP security tool in one server: OWASP MCP Top 10, secrets, supply chain, TLS/DNS
    More from GuardBee →
    A
  • MCP Security Guard
    Audit MCP servers for tool poisoning, rug pulls and supply-chain risk (OWASP MCP Top 10).
    A
  • Inkog
    Security co-pilot for AI agents. Scan for vulnerabilities, audit MCP servers, verify governance.
    B