Guardrails for AI coding agents: blocks secret reads, destructive commands, and unapproved MCP servers before the tool call runs. Ships project profiles, capability locks, a context engine, and task verification.
Cross-referenced across 55 tracked directories
#26071
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
7/25/2026
First Seen
Recently added to the ecosystem
Run an AI-powered security scan to analyze this package's source code for vulnerabilities, prompt injection vectors, data exfiltration risks, and behavior mismatches.
Scans fetch actual source code from the GitHub repository, not just the README.
Darko893
AI-powered web scraping MCP server with Cloudflare bypass, JavaScript rendering, and structured data extraction via the Haunt API. Pay-per-use with generous free tier.
...morenandakishoreleburu89
Comprehensive security guards for LLM-powered and agentic AI applications - 18+ protection layers covering OWASP Top 10 for LLMs 2025, Agentic Applications 2026, and MCP Security. Features prompt injection (PAP/persuasion), multi-modal attacks, RAG poison
...moreGitHub Actions
MCP server for [Clamp](https://clamp.sh) analytics. Gives your AI assistant read access to pageviews, visitors, referrers, countries, devices, custom events, and conversion funnels. Pro plans can create funnels and set up metric alerts.
...morebitgett
Q402 — gasless USDC/USDT payments across 7 EVM chains, callable from any MCP client.