Skip to main content
Glama

Project Shield

Security scanner for MCP servers and AI-generated code.

One command to security-grade your MCP server.

Installation

npm install -g project-shield

Or use directly with npx:

npx project-shield scan .

Related MCP server: agent-audit

MCP Server Configuration

Add to your MCP client config:

{
  "mcpServers": {
    "project-shield": {
      "command": "npx",
      "args": ["-y", "project-shield", "scan", "."]
    }
  }
}

Tools

scan

Security scan a directory or MCP server project. Returns A-F grade with detailed findings.

Parameters:

  • path (string, required) - Directory to scan

  • format (string, optional) - Output format: text, json, badge

grade

Get the security grade for a project without full report.

evidence

Generate a tamper-proof Evidence Pack with SHA-256 hashed scan results.

What it detects

Layer

What

How

Secrets

API keys, tokens, credentials

Regex + entropy + context analysis

PII

Email, phone, SSN

Pattern matching + checksum validation

Prompt Injection

Attacks in MCP tool descriptions

Heuristic + pattern detection

MCP Misconfig

Missing auth, open permissions, no logging

Config rule engine

Security Grades

Grade

Meaning

A

Excellent - ship with confidence

B

Good - minor improvements suggested

C

Clean - some issues to address

D

Warning - fix before deploy

E

Warning - significant issues found

F

Locked - deployment blocked until fixed

Features

  • 275+ detection rules across 4 security layers

  • A-F grading system with automatic deploy lock on F

  • Evidence Packs - SHA-256 hashed, tamper-proof scan results

  • Fix-it guides - actionable remediation for every finding

  • Badge system - verifiable security badges for your projects

  • MCP-native - scans MCP protocol-level security, not just code

Pricing

Plan

Price

Scans

Features

Free

$0

5/month

Basic reporting

Pro

$29/month

50/month

PDF reports, Evidence Packs

Team

$99/month

Unlimited (5 users)

CI/CD integration

Enterprise

$299+/month

Custom

SSO, audit trails

License

MIT

A
license - permissive license
-
quality - not tested
D
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    -
    quality
    C
    maintenance
    Scans MCP servers for prompt injection, supply chain attacks, excessive permissions, and code execution risks. Includes an offline blacklist that catches known-compromised packages like LiteLLM 1.82.7/1.82.8 and Trivy with zero latency.
    Last updated
    18
    MIT
  • A
    license
    -
    quality
    C
    maintenance
    Security scanner for MCP servers. Detects prompt injection, command injection, auth bypass, and excessive permissions across tools, resources, and prompts.
    Last updated
    38
    2
    MIT
  • A
    license
    -
    quality
    A
    maintenance
    Static security scanner for MCP server code, AI agent skills, and plugins. Detects 61 attack patterns across 4 severity levels — credential exfiltration, prompt injection, code execution, seed phrase harvesting, auth bypass, path traversal — with zero dependencies and 68+ real CVEs found in the wild.
    Last updated
    50
    5
    MIT

View all related MCP servers

Related MCP Connectors

  • Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.

  • Scan any public GitHub MCP-server repo for security issues. 37 MCP-specific L1 rules, 8 languages.

  • Zero-config MCP security scanner for AI-generated apps. 25K+ vulnerability patterns.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Whitening-Sinabro/project-shield-docs'

If you have feedback or need assistance with the MCP directory API, please join our Discord server