Search

Governance runtime for AI-generated code. Scan, gate, and trace compliance automatically.

Official MCP (Model Context Protocol) server for Claw GRC — the AI-native GRC platform. Connect any MCP-compatible AI assistant to your compliance data.

MCP server for Docker stack automation — generate, audit, and tune Docker Compose stacks inside Claude Code. Pure logic, no API keys, $0 to run.

Interven AI firewall — TypeScript SDK. Scan agent tool calls before they execute. Block malicious requests, redact PII/secrets, route risky actions to human approval.

AI agent permission and tooling surface diffs for pull request review.

Detect AI-hallucinated packages, phantom dependencies, and stale APIs in your codebase. Open-source CI/CD quality gate with local Ollama support — zero API cost.

ASCEND SDK - Enterprise AI Governance with fail mode, circuit breaker, and MCP integration

MCP supply chain scanner - detect tool poisoning, prompt injection, and shadowing attacks

Zero-Trust Data Sanitization (ZTDS) MCP Server for AI IDEs and Claude Desktop. Locally scrubs PII, secrets, and credentials before sending context to LLMs.

Scan a project for leaked secrets, risky MCP configs, and unsafe automation before handing it to an AI coding agent (Claude Code, Cursor, Codex). Zero dependencies, runs locally.

Netlify command line tool

Varlock plugin to load secrets from AWS (supports both Secrets Manager and Systems Manager Parameter Store)

AI DevOps Automation Engine

⚡ StringRay ⚡: Bulletproof AI orchestration with systematic error prevention. Zero dead ends. Ship clean, tested, optimized code — every time.

A Model Context Protocol (MCP) server for integrating with the AbuseIPDB API

Permission tiers, approval gates, and audit logging for MCP servers — the server is the gatekeeper.

Library for Ed25519-signed MCP tool manifests, runtime spawn-attestation, default-deny argument sanitizer. Layer-2 mitigation for marketplace-poisoning, CVE-2025-69256, CVE-2025-61591.

Lint OpenAPI specs for AI agent safety — detect risky operations, missing guards, destructive endpoints, and schema issues before exposing APIs to LLMs and agents

Local-first MCP agent quality and execution layer with guarded local tools

The ultimate AI token-saving MCP middleware — compression, caching, injection shield, multi-server routing, and more.