correctover-mcp-scanner 3.0.0

Correctover MCS v3.0 — MCP Server Security Boundary Scanner. Automated vulnerability audit for the Model Context Protocol ecosystem.

Correctover-MCS v3.0.0

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

---

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

MIT — © 2026 Correctover. All rights reserved.

Contact

• Website: correctover.com
• Email: [e-mail]
• GitHub: github.com/Correctover