MCPSafe.io
RegistryThreatsMethodologyDocsPricingScanSign in
MCPSafe.io

Security checks for MCP servers — public packages and private repos, fast or deep.

Legal

Privacy PolicyCookie PolicyTerms of ServiceSecurity disclosure

Resources

State of MCP SecuritySupportSystem statusMade in Germany 🇩🇪

© 2026 MCPSafe. All rights reserved.

GDPR — Privacy Policy

Public dashboard · Last refresh 5d ago

The State of MCP Security

Live numbers from MCPSafe’s scan cache. Updated every few minutes as new servers are scanned.

Packages scanned

6

Graded A or B

4

67% of catalog

Graded D or F

1

17% of catalog

Total findings

27

across latest scans

Grade distribution

6
  • A0(0%)
  • B4(67%)
  • C
1
(17%)
  • D0(0%)
  • F1(17%)

    • Top finding categories

    • verbose errors
      207
    • resource exhaustion
      5
    • readiness
      5
    • server configuration
      5
    • data exfiltration
      2
    • vulnerable dependency
      1
    • insecure container image
      1

    Top MCP packages

    Most popular

    Ranked by GitHub stars.

    1. 1.Bpunkpeye/awesome-mcp-servers90,647 ★
    2. 2.Cupstash/context758,969 ★
    3. 3.Cgithub:github/github-mcp-server@1add5fe2310430,137 ★
    4. 4.Dgithub:modelcontextprotocol/python-sdk@e8e64842781c23,113 ★
    5. 5.Btadata-org/fastapi_mcp11,939 ★
    6. 6.Dgithub:LaurieWired/GhidraMCP@27f316f801398,965 ★
    7. 7.Bwong2/awesome-mcp-servers4,203 ★
    8. 8.Dcloudflare/mcp-server-cloudflare3,935 ★
    9. 9.Cgithub:bethington/ghidra-mcp@de5f9ac9c8be2,946 ★
    10. 10.Bgithub:GongRzhe/Office-Word-MCP-Server@a3bbbb6d61672,111 ★

    Highest rated

    A-graded packages, ranked by safety score.

    1. 1.Avercel-labs/mcp-for-next.jsscore 96

    By package source

    How the catalog splits across npm, PyPI, GitHub, and Docker Hub — and which source ships the safest MCP servers on average.

    npm

    50%

    3

    scanned

    Avg score
    88.3
    Graded A/B
    3 (100%)
    Graded D/F
    0
    Findings
    5

    PyPI

    33%

    2

    scanned

    Avg score
    80
    Graded A/B
    1 (50%)
    Graded D/F
    0
    Findings
    22

    GitHub

    17%

    1

    scanned

    Avg score
    0
    Graded A/B
    0 (0%)
    Graded D/F
    1
    Findings
    0

    Top publishers

    • truongbuinh
      1

    Subscribe

    Get the monthly State of MCP Security in your inbox.

    One email per month. Quotable stats, new threat patterns, and the packages worth watching. Unsubscribe anytime.

    Share:X / TwitterLinkedIn

    How these numbers are built

    • Every counter is derived from the most recent scan of each package in our cache. Older scans do not double-count.
    • Grade distribution uses the same A–F scale shown on the scan report. See /threats for the detection categories behind each finding.
    • Top publishers are inferred from GitHub package URLs (the owner in github.com/owner/repo). Packages from npm, PyPI, and Docker don’t count here today.
    • Browse the full catalog from the registry.

    Frequently asked

    What is an MCP server?+
    Model Context Protocol (MCP) servers expose tools, resources, and prompts to AI agents. They sit between an LLM and an underlying system — your filesystem, a database, an API — and execute privileged actions on the agent's behalf, which makes their security profile materially different from a typical web service.
    Where does this data come from?+
    Every counter is derived from the most recent MCPSafe scan of each public MCP server in our cache. Older scans don't double-count. Findings are produced by the same rule engine that powers individual scan reports — see our methodology page for the rubric.
    How is the safety grade calculated?+
    Each server gets a 0-100 safety score that combines static analysis findings, supply-chain signals (typosquatting, CVEs), permission and network posture, and LLM-judged behavioral risks. Scores map to A through F bands. The full scoring rubric is published — we don't keep it secret.
    How often is this dashboard updated?+
    The dashboard re-reads its source-of-truth aggregate every few minutes. Individual server scans are re-run when their version changes, when a new rule ships, or on demand from the public registry.
    Can I scan a private MCP server?+
    Public scans are free and require no account. Private repository scanning is available on paid plans — see the pricing page for details.
    Can I cite or embed this data?+
    Yes — the dataset is intended to be quoted in research, blog posts, and security write-ups. Please link back to this page and credit MCPSafe. An embeddable widget for partner sites is on the roadmap.