MCP servers: Security

Security & trust layer for AI agents. Scan an MCP server or skill *before* you install it (`scan_mcp_plugin`, `scan_skill`) — flags exfiltration, prompt-injection sinks, dangerous capabilities, install hooks and obfuscation → PROCEED/CAUTION/BLOCK. Plus `vet_endpoint` (endpoint safety verdict before an agent calls or pays it) and 25 more tools: vuln scans, threat intel, compliance (SOC 2/ISO 27001/HIPAA), code security (SAST/secret/dependency), identity — 28 total. Per-call billing via API key or x402 USDC on Base; free discovery tier.

Cross-repository code knowledge graph MCP server for Java, Kotlin, JavaScript, and TypeScript. Indexes source into embedded KuzuDB via tree-sitter; 30+ tools for call-flow tracing, multi-hop taint analysis (OWASP/CWE/PCI/STIG reports), entry-point reachability filtering, performance hotspot detection, and license compliance — without reading source files. 95% fewer tokens vs source-reading baseline. `pip install orihime`

claude mcp add orihime -- pip install orihime

Zero-knowledge password manager with MCP credential gateway. BIP-39 seed phrase recovery, deterministic passwords, policy-gated AI agent access (scope, rate limits, time windows, step-up approval), 70+ API key providers, and hash-chain audit trail. Go + Next.js + TypeScript.

Security-focused MCP server that provides safety guidelines and content analysis for AI agents.

Security and governance proxy for MCP infrastructure. Enforces YAML-configurable policies (blocklists, rate limits, token budgets), tracks real token costs via tiktoken, monitors server health with live JSON-RPC probes. Features include OAuth 2.1/OIDC with RBAC, web dashboard with Prometheus metrics, payload normalization against encoding bypasses, semantic shell AST analysis, mTLS zero-trust networking, circuit breakers, and a formal STRIDE threat model. 168 tests across 16 suites. Install: npm install -g @mcp-guardian/server

MCP server for analyzing ROADrecon gather results from Azure tenant enumeration

Open-source AWS security scanner with attack chain detection, breach cost estimation, and copy-paste remediation (CLI + Terraform). 47 checks, 16 attack chain rules. First free standalone AWS security MCP server.

URL fetcher and HTML-to-markdown converter with three-layer prompt injection defense: pre-extraction sanitization of hidden/off-screen elements and non-printing Unicode, 15-pattern risk scanning (HIGH/MEDIUM/OK), and per-request session-salt content boundary wrapping.

AI Agent Security Middleware & MCP Server with 8-layer defense including prompt injection detection, DLP data flow tracking, command blocking, and PII detection. 7 MCP tools, zero dependencies.

Enterprise AI governance layer with 29 tools: MAI decision classification (Mandatory/Advisory/Informational), hash-chained forensic audit trails, human-in-the-loop gates, compliance mapping (NIST AI RMF, EU AI Act, ISO 42001), governed memory packs, and site reliability tools.

AI code security scanner MCP server. Detects 9 categories of threats in AI-generated code (invisible Unicode, Trojan Source, homoglyphs, Glassworm steganography, rules file backdoors, dependency typosquatting, obfuscation) using static analysis plus CodeBERT deep learning. Runs locally, free tier.

Security scanner for AI agents that detects prompt injections using 42+ regex patterns