Skip to main content

Correctover-MCS v3.0.0


🇨🇳 国内用户 · 支付宝一键购买

本工具的合规授权与批量能力可通过支付宝 SkillPay 获取:


MCP Server Security Boundary Scanner — Automated vulnerability audit for the Model Context Protocol ecosystem

Version Python License


What is MCS?

Correctover-MCS (MCP Scanner) is an automated security scanner that audits MCP (Model Context Protocol) servers for vulnerabilities. It identifies security boundary violations, injection points, privilege escalation paths, and data exfiltration risks in MCP server implementations.

Built on CCS verification principles — every finding is backed by code-level evidence and reproducible PoC.

Core Capabilities

  • Automated Audit: Scan any MCP server implementation for known vulnerability patterns
  • Signature Engine: 50+ vulnerability signatures across SSRF, RCE, auth bypass, data exposure
  • Code Analysis: Static analysis + dynamic testing with containerized sandboxes
  • CVSS Scoring: Automated severity classification with CVSS v3.1 scoring
  • Report Generation: Professional audit reports with PoC, impact analysis, and remediation

Quick Start

pip install correctover-mcs

Scan a target

# Scan a GitHub repository
ccs-scan scan --repo https://github.com/example/mcp-server

# Scan a PyPI package
ccs-scan scan --pypi mcp-server-example

# Scan with custom signatures
ccs-scan scan --repo https://github.com/example/mcp-server --signatures custom-sigs/

# Generate full report
ccs-scan scan --repo https://github.com/example/mcp-server --report full --format pdf

API Usage

from ccs_scanner import MCPServerScanner

scanner = MCPServerScanner()
results = scanner.scan_repo("https://github.com/example/mcp-server")

for vuln in results.vulnerabilities:
    print(f"[{vuln.cvss}] {vuln.title}")
    print(f"  File: {vuln.file_path}:{vuln.line}")
    print(f"  PoC: {vuln.poc_code}")

Vulnerability Categories

Category Signature Count Max CVSS Examples
SSRF 12 9.3 URL parameter injection, proxy abuse
RCE 8 9.8 Container escape, command injection
Auth Bypass 10 9.1 Token timing attack, missing auth
Data Exposure 7 8.8 Sensitive path access, no ACL
Supply Chain 6 8.6 Unsigned images, dependency confusion
DoS 5 7.5 Resource exhaustion, infinite loops

Architecture

┌─────────────────────────────────────────┐
│              MCS Scanner v3.0.0         │
│  ┌──────────┬──────────┬──────────────┐ │
│  │  Target   │ Signature│    Code     │ │
│  │ Fetcher   │  Engine  │  Analyzer   │ │
│  ──────────┴──────────┴──────────────┘ │
│  ┌──────────┬──────────┬──────────────┐ │
│  │ Sandbox   │   CVSS   │   Report    │ │
│  │ Executor  │ Scorer   │ Generator   │ │
│  └──────────┴──────────┴──────────────┘ │
└─────────────────────────────────────────┘

Performance

Metric Value
Scan time (avg repo) 45-120s
Signatures loaded 50+
False positive rate <5%
True positive rate >90% (verified)

Deployment

Local

pip install correctover-mcs
ccs-scan scan --repo <target>

Docker

FROM python:3.12-slim
RUN pip install correctover-mcs
ENTRYPOINT ["ccs-scan"]
docker build -t correctover-mcs .
docker run correctover-mcs scan --repo <target>

License

Elastic License 2.0 — © 2026 Correctover. See LICENSE.

Contact

Metadata

Release files for correctover-mcp-scanner 3.0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for correctover-mcp-scanner 3.0.1
File Size Uploaded Provenance
correctover_mcp_scanner-3.0.1.tar.gz 33.4 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for correctover-mcp-scanner 3.0.1
File Interpreter ABI Platform
correctover_mcp_scanner-3.0.1-py3-none-any.whl Python 3 none any Details

Total release size: 70.5 kB

Release files / correctover_mcp_scanner-3.0.1.tar.gz

Download URL correctover_mcp_scanner-3.0.1.tar.gz
Size 33.4 kB
Tags Source
SHA-256 checksum
How to use checksums
cbd6519c4b3bc292c5bb4ec1cb066919f68f6fa4ba240f3d16d6f28658220034
BLAKE2b-256 checksum
How to use checksums
4fca71116026e7c8179ed62c765d4a7df11867e39926fa298db0db4570648ed9
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.12

Release files / correctover_mcp_scanner-3.0.1-py3-none-any.whl

Download URL correctover_mcp_scanner-3.0.1-py3-none-any.whl
Size 37.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
e55da9160463056c258ade4d035e78eecf49e57efae39fc86118704e645061d2
BLAKE2b-256 checksum
How to use checksums
a62379adadf98ae2a0621b581f5df91401f94cf530dbb9ee61a33d040510fe64
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.12

Security for correctover-mcp-scanner 3.0.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page