Developer · Local MCP server
Prompt Injection Scanner
Scans RAG content/scraped pages for indirect prompt injection.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.4hmetuyar/prompt-injection-scanner- Version
- 0.2.2
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- npm
- Published
- 2026-10-02
- Updated
- 2026-10-02
- Publisher
- 4hmetuyar (GitHub) · 26 servers with pages here
- Repository
- github.com/GuardBee/guardbee-mcp (folder packages/prompt-injection-scanner)
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| npm | @guardbee/mcp-prompt-injection-scanner | 0.2.2 | stdio |
How to connect Prompt Injection Scanner
Prompt Injection Scanner runs locally from a Node.js package published to the npm registry: @guardbee/mcp-prompt-injection-scanner version 0.2.2. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx — the usual command is npx -y @guardbee/mcp-prompt-injection-scanner@0.2.2.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"prompt-injection-scanner": {
"command": "npx",
"args": [
"-y",
"@guardbee/mcp-prompt-injection-scanner@0.2.2"
]
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More from 4hmetuyar (GitHub)
| Server | Runs |
|---|---|
| Llm RedteamActive jailbreak/extraction/obfuscation red-teaming for live LLM endpoints. | Local · stdio |
| MCP Config AuditorScans Cursor/Claude/Windsurf/VS Code MCP configs for unpinned versions, secrets, typosquats. | Local · stdio |
| MCP Server AuditorScans MCP server tool definitions for excessive agency, injection sinks, hardcoded secrets. | Local · stdio |
| Memory Poisoning ScannerScans agent code for untrusted input poisoning persistent cross-session memory. | Local · stdio |
| Model ScannerScans ML model files (PyTorch, safetensors, Keras, ONNX) for supply-chain risks. | Local · stdio |
| Oauth AuditorScans MCP server auth code for OAuth 2.1 anti-patterns: token passthrough, missing audience. | Local · stdio |
| Prompt Leak ScannerCatches leaked credentials and PII in outbound LLM prompts. | Local · stdio |
| Rug Pull DetectorBaselines an MCP server's tools and detects tool-definition changes after approval. | Local · stdio |
| Secret ScannerScans files for leaked secrets and API keys. | Local · stdio |
| Security ProxyMCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log. | Local · stdio |
| Security SuiteBundle of secret-scanner, dependency-auditor, ssl-inspector, and dns-intelligence. | Local · stdio |
| Slopsquat ScannerChecks declared npm/PyPI dependencies against real registries to catch slopsquatting. | Local · stdio |
More developer servers
| Server | Runs |
|---|---|
| ProjectPulse MCPMonitor GitHub repo health, DORA metrics and CI signals from your AI assistant. | Local · stdio |
| ProjGraph MCP ServerAnalyze.NET solutions: Generate Mermaid graphs, ERDs, class diagrams, and project metrics. | Local · stdio |
| Prometheus MCP ServerMCP server providing Prometheus metrics access and PromQL query execution for AI assistants. | Local · stdio |
| Prompt CompassDecision-only prompt routing and firewall checks for local/cloud routing, PII and jailbreak risk. | Remote & Local · HTTP, stdio |
| Prompt TimeClaude Desktop reminders for Windows. Survives MSIX boundary; persists across restarts. Zero deps. | Local · stdio |
| prompt-protectionScan prompts, tool definitions and model output for injection, and guard agent tool calls. | Local · stdio |
| promptarch.aiResearch-backed linting + generation for agent context files (CLAUDE.md, AGENTS.md, Cursor rules). | Remote · HTTP |