security MCP Server
Practical audit tools and controls for securing MCP servers and agentic AI tool access.
Discovered via github-topic:model-context-protocol and last synced 3mo ago.
Install instructions not detected yet
Check the source repository for the latest setup steps.
Package runner is used without an obvious package version pin
MCP-003
Remote MCP server has no clear authentication signal
Rule
Remote MCP server uses unencrypted HTTP
Filesystem-like tool lacks a read-only signal
Shell or evaluator command can execute arbitrary code
MCP-004
Risk
Server has no visible owner or risk owner metadata
Dangerous execution flags are present
Credential-like URL userinfo values are configured inline
Browser session or profile data is exposed to the MCP server
Docker-based MCP server image is not pinned to an immutable digest
Kubernetes service account access is exposed to the MCP server
Purpose
Tool auto-approval is configured with a wildcard
Browser debugging interface is exposed to the MCP server
CI/CD credential context is exposed to the MCP server
Secret-like URL query parameter values are configured inline
Environment file is exposed to the MCP server
Container runtime socket access is exposed to the MCP server
Broad filesystem access is granted
TLS certificate validation is disabled
External-action tools are configured for automatic approval
Database client credential context is exposed to the MCP server
Purpose
Docker configuration uses privileged or host-level access
Docker socket access is exposed to the MCP server
Cloud metadata endpoint or wildcard network scope is reachable by the MCP server
Package registry credential context is exposed to the MCP server
Secret-like values are configured inline in environment variables
Secret-like HTTP header values are configured inline
Authentication scopes or permissions look overbroad
SSH agent socket access is exposed to the MCP server
Secret-like command argument values are configured inline
Credential-bearing local path is exposed to the MCP server
Git credential helper access is exposed to the MCP server
MCP-005
Cloud CLI credential context is exposed to the MCP server
真实性验证技能。分析用户提供的信息、消息、图片或内容，判断其真实性和可信度，识别虚假信息、AI生成内容或伪造内容。
Container escape is a critical attack technique where an adversary breaks out of container isolation to access the host system or other containers. Detection involves monitoring for escape indicators
Pod Security Standards (PSS) define three levels of security policies -- Privileged, Baseline, and Restricted -- enforced by the Pod Security Admission (PSA) controller built into Kubernetes 1.25+. PS
Implements eBPF-based security monitoring using Cilium Tetragon for real-time process execution tracking, network connection observability, file access auditing, and runtime enforcement. Covers TracingPolicy CRD authoring with kprobe/tracepoint hooks, in-kernel filtering via matchArgs/matchBinaries selectors, JSON event export, and integration with SIEM pipelines. Use when building kernel-level runtime security observability for Linux hosts or Kubernetes clusters.
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
Open-source sandboxed agent harness for teams. Giving every employee a secured personal agent.
AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️
A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)
Learn how to use the absolute-audit Claude skill. Complete guide with installation instructions and examples.
Learn how to use the token-scam-analysis Claude skill. Complete guide with installation instructions and examples.
Learn how to use the absolute-upgrade Claude skill. Complete guide with installation instructions and examples.