repo-forensics MCP — Use Cases, Install & Live Demo

Why use it

Key features

18 scanners covering distinct threat surfaces
Skill-specific: SKILL.md poisoning, Unicode smuggling, OpenClaw patterns
MCP-specific: tool poisoning, rug-pull enablers
Correlation engine connects findings across scanners to catch compound attacks
Zero dependencies — pure audit, safe to run on anything

Live Demo

What it looks like in practice

repo-forensics-skill.replay ▶ ready

0/0

Install

Pick your client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "repo-forensics-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/alexgreensh/repo-forensics",
        "~/.claude/skills/repo-forensics"
      ],
      "_inferred": true
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "repo-forensics-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/alexgreensh/repo-forensics",
        "~/.claude/skills/repo-forensics"
      ],
      "_inferred": true
    }
  }
}

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "repo-forensics-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/alexgreensh/repo-forensics",
        "~/.claude/skills/repo-forensics"
      ],
      "_inferred": true
    }
  }
}

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "repo-forensics-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/alexgreensh/repo-forensics",
        "~/.claude/skills/repo-forensics"
      ],
      "_inferred": true
    }
  }
}

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "repo-forensics-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/alexgreensh/repo-forensics",
        "~/.claude/skills/repo-forensics"
      ]
    }
  ]
}

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

{
  "context_servers": {
    "repo-forensics-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/alexgreensh/repo-forensics",
          "~/.claude/skills/repo-forensics"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

claude mcp add repo-forensics-skill -- git clone https://github.com/alexgreensh/repo-forensics ~/.claude/skills/repo-forensics

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use repo-forensics

Audit a third-party skill before you clone it into ~/.claude/skills

👤 Anyone installing skills from strangers on GitHub ⏱ ~15 min beginner

When to use: Someone sent you a cool-looking skill link. Before clone, you want to know if it's safe.

Prerequisites

repo-forensics installed — git clone https://github.com/alexgreensh/repo-forensics ~/.claude/skills/repo-forensics

Flow

Point at the target repo URL

Use repo-forensics. Scan https://github.com/<author>/<skill> with the skill_threats, secrets, dataflow, and lifecycle scanners. Report findings.✓ Copied

→ Per-scanner report with severity flags
Read correlated findings

Any correlations across scanners — e.g. a secret-leak path plus a lifecycle hook?✓ Copied

→ Correlation summary

Outcome: A go / no-go decision grounded in scanner output, not vibes.

Pitfalls

Trusting a green scan as full proof of safety — Scanners are strong floor, not a ceiling — still read SKILL.md

Combine with: github · filesystem

Audit an MCP server for tool poisoning and rug-pull patterns

👤 Teams onboarding a new MCP into a production agent stack ⏱ ~20 min intermediate

When to use: Before adding a new MCP server to an agent with real permissions.

Flow

Run MCP-focused scanners

Scan this MCP server repo with mcp_security, skill_threats, integrity, and dast.✓ Copied

→ Findings focused on tool descriptions and install scripts
Check git history for identity spoofing

Run git_forensics on the same repo — any spoofed commits?✓ Copied

→ Author / signing analysis

Outcome: An MCP security dossier before you wire it into your agent.

Run post-incident scanners after a suspicious install

👤 Anyone who just ran npm/pip install and feels uneasy ⏱ ~15 min intermediate

When to use: Install finished with unexpected behavior; you want to know if something landed.

Flow

Run post_incident + entropy scans

Run post_incident scanner on ~/.npm and the current project. Also entropy scan the installed packages.✓ Copied

→ Flags for suspicious cached artifacts or encoded payloads

Outcome: Evidence of whether to rotate secrets and rebuild.

Pitfalls

Running scans from the potentially-compromised shell — Run from a fresh shell or another machine when in doubt

Combinations

Pair with other MCPs for X10 leverage

repo-forensics-skill + github

Pull a PR's diff and scan only the added files

Fetch PR #123 and run repo-forensics just on the files it adds.✓ Copied

repo-forensics-skill + filesystem

Scan a locally cloned repo and save a JSON report

Scan ./suspicious-repo and write findings.json next to it.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call
skill_threats	repo path	Any skill audit
mcp_security	repo path	MCP audits
secrets	repo path	Always
dataflow	repo path	Suspicious egress concerns
lifecycle	repo path	Pre-install
git_forensics	repo path	Checking maintainer identity
entropy	repo path	Obfuscation suspected
sast	repo path	General code risk

Cost & Limits

What this costs to run

API quota: None
Tokens per call: Moderate — scanner output summarization can grow
Monetary: Free
Tip: Run only the scanners relevant to the threat model (skills → skill_threats; MCP → mcp_security)

Security

Permissions, secrets, blast radius

Credential storage: None — scanner is read-only

Data egress: Local-only by default

Never grant: Write access to the repo under audit

This is a defensive tool. Don't use scanner output to stress-test your own targets — it's not a pentest kit.

Troubleshooting

Common errors and fixes

Scanner reports 0 findings on obviously sketchy repo

Ensure you ran against the full repo path, not a subset; check scanner selection

Verify: repo-forensics list-scanners

False positives flood the report

Filter by severity; focus on high/critical; use correlation to prioritize

Alternatives

repo-forensics vs others

Alternative	When to use it instead	Tradeoff
claude-cybersecurity	Your code needs OWASP-style app security review rather than supply-chain vetting	Different focus — app logic vs install-time threats
gitleaks / trufflehog	You only need secret scanning	Single-scanner, not correlation

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills