Developer · Local MCP server

Security Proxy

MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log.

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/security-proxy
Version
1.4.0
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/security-proxy)
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
npm@guardbee/mcp-security-proxy1.4.0stdioNone declared

How to connect Security Proxy

Security Proxy runs locally from a Node.js package published to the npm registry: @guardbee/mcp-security-proxy version 1.4.0. 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-security-proxy@1.4.0.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "security-proxy": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-security-proxy@1.4.0"
      ]
    }
  }
}

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)

ServerRunsEndpoint or package
Model ScannerScans ML model files (PyTorch, safetensors, Keras, ONNX) for supply-chain risks.Local · stdionpm: @guardbee/mcp-model-scanner
Oauth AuditorScans MCP server auth code for OAuth 2.1 anti-patterns: token passthrough, missing audience.Local · stdionpm: @guardbee/mcp-oauth-auditor
Prompt Injection ScannerScans RAG content/scraped pages for indirect prompt injection.Local · stdionpm: @guardbee/mcp-prompt-injection-scanner
Prompt Leak ScannerCatches leaked credentials and PII in outbound LLM prompts.Local · stdionpm: @guardbee/mcp-prompt-leak-scanner
Rug Pull DetectorBaselines an MCP server's tools and detects tool-definition changes after approval.Local · stdionpm: @guardbee/mcp-rug-pull-detector
Secret ScannerScans files for leaked secrets and API keys.Local · stdionpm: @guardbee/mcp-secret-scanner
Security SuiteBundle of secret-scanner, dependency-auditor, ssl-inspector, and dns-intelligence.Local · stdionpm: @guardbee/security-suite
Slopsquat ScannerChecks declared npm/PyPI dependencies against real registries to catch slopsquatting.Local · stdionpm: @guardbee/mcp-slopsquat-scanner
Tool Poisoning ScannerScans MCP tool definitions for hidden instructions and confused-deputy sinks.Local · stdionpm: @guardbee/mcp-tool-poisoning-scanner
Toxic Flow AuditorFinds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress.Local · stdionpm: @guardbee/mcp-toxic-flow-auditor
Unbounded Consumption AuditorScans LLM/agent code for Unbounded Consumption / denial-of-wallet risks (OWASP LLM Top 10 2026 #6)Local · stdionpm: @guardbee/mcp-unbounded-consumption-auditor
Vector Store ScannerProbes vector-database endpoints for unauthenticated exposure of embeddings/RAG data.Local · stdionpm: @guardbee/mcp-vector-store-scanner

More developer servers

All 6,250 →
ServerRunsEndpoint or package
Security Intel MCPCVE lookups (NVD) and dependency-manifest audits (OSV) for AI agents. No API keys.Remote · HTTPsecurity.selflabbs.com
Security MCPZero-key security toolkit: grade sites A+ to F, check CVE exploits, plain-English attack defenses.Local · stdioPyPI: security-mcp
Security OrchestraMulti-agent MCP platform for data centers and critical power.Local · stdionpm: @securityorchestra/security-orchestra
Security PreflightStatic MCP, source-code and injection-indicator checks with redacted signed receipts.Remote · HTTPmcp.viridis-security.com
Security ToolsFree front-end security check for any website: a grade plus the secrets and keys it exposes.Remote · HTTPrangercheck.com
Security Txt Cra Lint13 rules that decide whether a vulnerability report ever reaches you.Local · stdionpm: @readystack/security-txt-cra-lint
SecurityScanScan GitHub-hosted AI skills for vulnerabilities: prompt injection, malware, OWASP LLM Top 10.Remote · HTTPapisecurityscan.net