security MCP Server
Security, cost, and health governance proxy for MCP infrastructure — YAML policy engine, OAuth 2.1/OIDC, web dashboard, mTLS, semantic shell analysis, STRIDE threat model
Discovered via github-topic:mcp and last synced 2mo ago.
1. Install the package
npx @mcp-guardian/server
2. Add to claude_desktop_config.json
{
"mcpServers": {
"-mcp-guardian-server": {
"command": "npx",
"args": [
"@mcp-guardian/server"
]
}
}
}Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)
Purpose
Local dev only: use dashboard without Pro license
Full security/health report to stdout
Offline adversarial policy matrix (808+ fixtures)
Set `false` when running a second proxy alongside `dashboard:proxy`
Wall-clock duration for `real-life:continuous` (default `60`)
Legacy standalone SOC API (default `4040`; see [SOC-API.md](SOC-API.md))
Guardian home dir (semantic store, autopilot config)
Purpose
Dashboard port (default `4000`)
Traffic KPIs, error rate, token/cost series
Live WebSocket metrics
Role
What it does for you
Path to your rules file
What you see
Fix
Max raw JSON-RPC message size (default 10MB)
Daily spend alert threshold
Notes
Entry module
Plain meaning
Features
REST API + web UI
Yes
What it does
Require RBAC on `tools.allow` policy rules
Document
Yes
Local LLM endpoint
Also encrypt redacted argument snippets in audit (`true` + key above)
Config file
Where call history is stored (share this between proxy and test runners)
`~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json`
Max serialized tool-argument size after decode (default 50MB)
Skip login on localhost
Periodic MCP health probes (0 = disabled)
[docs/AUTOPILOT.md](docs/AUTOPILOT.md)
Semantic / AI features
Encrypt sensitive audit fields at rest
`~/.cursor/mcp.json`
How often to refresh OIDC JWKS (default 5 minutes)
How long to keep audit rows (default 30)
Wait for in-flight calls on shutdown (default 30s)
Export block/audit events to Splunk, Datadog, webhooks, etc.
[docs/ARCHITECTURE.md](docs/ARCHITECTURE.md)
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.