Search
prysmai
PrysmAI Python SDK for the proxy and MCP paths into one AI control plane. Capture traces, security findings, policy decisions, and governance evidence for production AI systems.
...morepi-permission-suite
eddie0521
Four approval modes + command-level security restrictions for the Pi coding agent. Act / Auto / Ask / Plan mode switching, rule engine, subagent auto-approval.
...morevirgil-crypto
rstp
Virgil JavaScript Crypto Library is a high-level cryptographic library that allows you to perform all necessary operations for secure storing and transferring data and everything required to become HIPAA and GDPR compliant.
...moresecflow
imsankz
SECflow — zero-cost security scanning for AI-driven repos: secrets (gitleaks), dependency vulns (trivy / npm audit), custom regex rules, and AI-ready fix reports.
...more@vantin/backendguard
vantin
AI backend engineering guardrails for NestJS, PostgreSQL, TypeORM, and Prisma — task-aware security/architecture/database context for AI coding agents, plus post-task compliance reporting.
...more@meedo01/agentscan
meedo01
Security & quality scanner for AI agent extensions — Claude skills, MCP servers, Cursor rules and agent instruction files. Like npm audit, but for the stuff you install into your coding agent.
...more@pinkpixel/keyper
sizzlebop
🔐 Modern self-hosted credential manager with zero-knowledge encryption, multi-user support, and emergency recovery. Store API keys, passwords, and secrets securely with your own Supabase database.
...more@bitofacoder/mcpaudit
bitofacoder
Security scanner for your installed MCP servers. Finds shell-exec tools, plaintext secrets, and unpinned supply chains across Claude Desktop, Claude Code, Cursor, and Windsurf configs.
...more@acegalaxy/ott-gateway
kanelr
Inbound message security gateway for bots — 5-layer default-deny (caller-validator, identity-resolver, rate-limit, audit, forward) for Telegram/WhatsApp/WeChat and other OTT platforms.
...more@smorky85/aurakit
smorky85
All-in-one Claude Code skill: build, fix, review, deploy with one /aura command. 36 modes, 6-layer security, auto-installs jq, ~55% token savings.
...morezenstack-graphql-builder
jase17
Automatically generate a complete GraphQL CRUD API from ZenStack schemas, including input types, filters, relation resolvers, custom directive support, security limits, and query projection parsing.
...more@snitchplugin/cli
snitchplugin
Local AI security scanner. Runs on your laptop with your own Claude Code, Codex, Gemini, or OpenRouter key. Source never leaves your machine. 68 categories, SARIF output, CI-ready.
...moresast-mcp-server
Abdellah
A standard MCP server for SAST tools (Bandit, njsscan, Bearer, Semgrep, Trivy, CodeQL, Checkov, Gitleaks, OSV-Scanner, ZAP) — scan code for security vulnerabilities from any AI agent
...more@goplus/agentguard
goplussecurity
GoPlus AgentGuard — Security guard for AI agents. Blocks dangerous commands, prevents data leaks, protects secrets. 20 detection rules, runtime action evaluation, trust registry.
...moreace-engine
hassekf
Architectural Coverage Engine — zero-dependency incremental architectural analysis for Laravel projects. Measures consistency, infers patterns, evaluates security baselines, and exposes an MCP server for LLM integration.
...more@nichtsam/helmet
GitHub Actions
Helps secure applications by setting HTTP response headers. Inspired by [`helmet`](https://github.com/helmetjs/helmet) and [`http-helmet`](https://github.com/mcansh/http-helmet).
...moreelasticsearch-mcp-vsee-stage
michaellei2006
Secure MCP server for Elasticsearch integration with comprehensive tools and Elastic Cloud support (fork with improved health check, get_index_fields tool, enhanced query flexibility, and consolidated analytics tools)
...moremcp-proxy-adapter
Vasiliy Zdanovskiy
Powerful JSON-RPC microservices framework with built-in security, authentication, proxy registration, queue-backed command execution for long-running operations, and configurable HTTP timeouts for mTLS connections
...moreaegis-audit
rsh1k
AI-powered smart contract security auditor — OWASP SC Top 10 (2026), MITRE ATT&CK, CWE, and NIST SSDF compliance outputs with a benchmarked detection engine
...morecerbere-ag-mcp
Christopher Dikesa
MCP server exposing CerbereAG runtime security checks (prompt injection, PII redaction, tool authorization) to any MCP-compatible AI agent (Claude, Cursor, Cline, custom agents).
...more