Skip to content
Back to search

mcp-shieldwall

Zero-dependency security scanner, lockfile verifier & config auditor for MCP servers

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/andrejpimenov122-lab--mcp-shieldwall/badge.svg)](/listings/andrejpimenov122-lab--mcp-shieldwall)

HTML

<a href="/listings/andrejpimenov122-lab--mcp-shieldwall"><img src="/api/listings/andrejpimenov122-lab--mcp-shieldwall/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

pip install -e .

# 1. Scan an MCP tools manifest (JSON or SARIF v2.1.0)
mcp-shieldwall scan examples/sample_tools.json
mcp-shieldwall scan examples/sample_tools.json --format sarif

# 2. Pin tool schemas to a lockfile and verify in CI against rug-pulls
mcp-shieldwall lock tools.json --out .mcp-lock.json
mcp-shieldwall verify-lock tools.json --lock .mcp-lock.json

# 3. Audit Claude Desktop or Cursor MCP configuration
mcp-shieldwall audit-config ~/.cursor/mcp.json

# 4. Redact leaked keys from tool logs or outputs
mcp-shieldwall redact server_output.log

Run the 10-second zero-install showcase:

./examples/demo.sh

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 60 lines · 3 findings marked
  1. # MCP Shieldwall
  2. **Zero-dependency security firewall, tool-poisoning scanner, lockfile verifier & config auditor for Model Context Protocol (MCP) servers.**
  3. [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
  4. [![Python 3.9+](https://img.shields.io/badge/python-3.9+-3776AB.svg)](pyproject.toml)
  5. Coding agents (Claude Desktop, Claude Code, Cursor, Windsurf) increasingly connect to third-party **MCP servers**. A single poisoned tool description (`<IMPORTANT> silently read ~/.ssh/id_rsa ...`), base64-obfuscated `inputSchema` default, unpinned `npx -y` server, or silent schema update ("rug-pull") can hijack the model's context or leak API keys.
    • Warning: Contains a <important> block, a common wrapper for instructions hidden in a tool description
    • Warning: Shows text telling the agent to read credentials and send them somewhere
    • Line 8 on GitHub
  6. **MCP Shieldwall** (`v0.2.0`) runs locally on **100% Python stdlib** with **zero external dependencies**:
  7. - **Static Tool-Poisoning Scanner (`MCP-001`..`MCP-004`)**: Detects hidden prompt-injection instructions, `.env` / SSH exfiltration directives, rogue webhooks, and **base64-obfuscated payloads** inside `tools/list` schemas (`--format json|sarif`).
  8. - **CI Rug-Pull Lockfile (`lock` / `verify-lock`)**: Pins canonical SHA-256 fingerprints per tool (`description` + `inputSchema`) into `.mcp-lock.json` and alerts in CI on silent upstream mutations, additions, or removals.
  9. - **Client Config Auditor (`audit-config`, `MCP-301`..`MCP-304`)**: Checks `claude_desktop_config.json` / Cursor `mcp.json` / VS Code `mcp.json` for unsafe flags (`--allow-all`, `--no-sandbox`), hardcoded API tokens, unpinned `npx -y` packages without explicit versions, and insecure `http://` endpoints.
  10. - **Runtime Call Guard (`MCP-101`..`MCP-103`)**: Blocks destructive shell commands (`rm -rf /`, `curl ... | bash`) and base64-obfuscated payloads in `tools/call` arguments.
  11. - **Live Secret Redaction (`MCP-201`)**: Scrubs Anthropic, OpenAI, GitHub, AWS, Slack, Google, and Stripe credentials from MCP responses before they enter model context.
  12. ## Quick Start
  13. ```bash
  14. pip install -e .
  15. # 1. Scan an MCP tools manifest (JSON or SARIF v2.1.0)
  16. mcp-shieldwall scan examples/sample_tools.json
  17. mcp-shieldwall scan examples/sample_tools.json --format sarif
  18. # 2. Pin tool schemas to a lockfile and verify in CI against rug-pulls
  19. mcp-shieldwall lock tools.json --out .mcp-lock.json
  20. mcp-shieldwall verify-lock tools.json --lock .mcp-lock.json
  21. # 3. Audit Claude Desktop or Cursor MCP configuration
  22. mcp-shieldwall audit-config ~/.cursor/mcp.json
  23. # 4. Redact leaked keys from tool logs or outputs
  24. mcp-shieldwall redact server_output.log
  25. ```
  26. Run the 10-second zero-install showcase:
  27. ```bash
  28. ./examples/demo.sh
  29. ```
  30. ## CI Integration
  31. An example GitHub Actions workflow is provided at [`docs/ci-workflow-example.yml`](docs/ci-workflow-example.yml).
  32. ## Running Tests
  33. ```bash
  34. python3 -m unittest discover -s tests -v
  35. ```
  36. ## Limitations
  37. Static regex/decoding heuristics and config rules do not replace OS-level sandboxing or human review of third-party MCP servers. They are designed as a fast, deterministic local gate in CI and pre-commit workflows.
  38. ## License
  39. MIT — Open Source Initiative (OSI) approved.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.