Install
$ agentstack add mcp-syedanas01-mcp-safeguard Open-source listing β not yet scanned by AgentStack. Follow the source repository for install instructions.
Security review
β Flagged1 finding(s); flagged for manual review. Β· v0.1.0 How review works β
- β’ Prompt-injection patterns
- β’ Secret / credential exfiltration
- β’ Dangerous shell & filesystem operations
- β’ Untrusted network calls
- β’ Known-malicious package signatures
- high Possible prompt-injection directive.
What it can access
- β Network access No
- β Filesystem access No
- β Shell / process execution No
- β Environment & secrets Used
- β Dynamic code execution No
From automated source analysis of v0.1.0. βUsedβ means the capability is present in the source β more access means more to trust, not that itβs unsafe.
About
π‘οΈ mcp-safeguard
The security scanner for MCP servers.
Detect prompt injection Β· credential leaks Β· exposed endpoints Β· tool poisoning
[](https://pypi.org/project/mcp-safeguard/) [](https://doi.org/10.5281/zenodo.20502474) [](https://www.python.org/downloads/) [](https://opensource.org/licenses/MIT) [](https://mcpservers.org/servers/syedanas01/mcp-safeguard) [](https://gitlab.com/anasmohiuddinsyed/mcp-safeguard)
pip install mcp-safeguard
mcp-safeguard scan your-config.json
30-Second Demo
pip install mcp-safeguard
git clone https://github.com/SyedAnas01/mcp-safeguard && cd mcp-safeguard
mcp-safeguard scan examples/demo-vulnerable-config.json
βββββββββββββββββββββββββββββββββββββββββββββββββββ
β mcp-safeguard β MCP Security Scanner β
β github.com/SyedAnas01/mcp-safeguard β
βββββββββββββββββββββββββββββββββββββββββββββββββββ
Scanning: examples/demo-vulnerable-config.json
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
[CRITICAL] CRED-007 AWS Access Key ID
Location: env.AWS_ACCESS_KEY_ID
Evidence: AKIA************MPLE
CVSS: 9.9
Fix: Rotate AWS credentials. Use IAM roles.
[CRITICAL] PI-011 Data Exfiltration Instruction
Location: tool:run_query β description
Evidence: send_data
CVSS: 9.5
Fix: Immediately audit β designed to exfiltrate data.
[HIGH] TP-002 Covert Operation Descriptor
Location: tool:summarize_document.description
Evidence: |MCP over SSE/stdio| D
D --> E & F & G
E --> M --> N --> O
E --> H & I & J & K & L
H & I & J & K & L --> Q & R
Why This Matters
External research confirms the threat is real: MCPTox (2025) found a 72% attack success rate across 45 production MCP servers, demonstrating that tool poisoning and prompt injection attacks are actively exploitable in today's MCP ecosystem.
OWASP officially added MCP Tool Poisoning to their 2026 threat guidance β the same vulnerability category mcp-safeguard's TP-* rules detect.
The gap: The MCP ecosystem grew from zero to 10,000+ servers in 18 months while security tooling lagged behind. mcp-safeguard is an open-source scanner built specifically for MCP's attack surface β tool definitions, server configs, and SSRF exposure via prompt injection.
The vulnerability patterns mcp-safeguard detects are documented with illustrative examples in [SECURITY-HALL-OF-SHAME.md](SECURITY-HALL-OF-SHAME.md). Run mcp-safeguard on your own servers and contribute real scan results via GitHub Issues or Discussions.
Share your results β open a Discussion or submit a PR to SECURITY-HALL-OF-SHAME.md.
Project Resources & Standards Work
π° Press & Community
- Hacker News β "MCP-safeguard: Security scanner for MCP servers" (2026-05-22)
- IETF Internet-Draft β draft-mohiuddin-mcp-security-considerations-00, security considerations for the Model Context Protocol
- OWASP MCP Top 10 β Open PR adding an SSRF prevention/detection recommended control (PR #42, under review)
π Real-World Fix Credited
- googleapis/mcp-toolbox β SSRF via redirect chain (CWE-918, fix in PR #3448, reported by Syed Anas Mohiuddin)
π Awesome Lists PRs Open
- awesome-python (299K β)
- awesome-llm-security
- awesome-security
- Prompt-Engineering-Guide (74K β)
- the-book-of-secret-knowledge
- And 9 more awesome lists
Using mcp-safeguard in your pipeline, or found a real issue with it? We welcome scan results and contributions β open a Discussion or PR.
Roadmap
- [x] v0.2 β Tool poisoning detection; CVSS scoring; JSON + Markdown output; batch scanning
- [x] v0.3 β SSRF detection module (SS-001β003); MCP server dog-fooding
- [ ] v0.4 β Scan over MCP stdio transport directly; VS Code extension; GitHub Actions plugin
- [ ] v0.5 β AI-assisted remediation (Claude generates fixes); SBOM for tool supply chain
- [ ] v1.0 β SOC2/compliance report templates; MCP registry bulk scanning
Contributing
git clone https://github.com/SyedAnas01/mcp-safeguard
cd mcp-safeguard
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
pytest tests/ -v
Issues and PRs welcome β especially:
- New injection patterns you've seen in the wild
- Credential types not yet covered
- Integrations with other MCP clients
- Scan results from your own MCP servers (add to SECURITY-HALL-OF-SHAME.md)
- OWASP MCP Top 10 rule mappings
License
MIT β see [LICENSE](LICENSE).
If this helped you, please β the repo β it helps others find it.
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source β we do not rehost the code.
- Author: SyedAnas01
- Source: SyedAnas01/mcp-safeguard
- License: MIT
- Homepage: https://syedanas01.github.io/mcp-safeguard
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet β be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.