Search

MCP server for discovering, evaluating, and comparing MCP servers via the MCPpedia catalog

MCP Permission Auditor — scan, enumerate, and risk-score all locally configured MCP servers

Idiomatic, zero-dependency, provider-agnostic Python safety layer for AI agents: least-privilege permissions, prompt/input/output guards, sandbox + SSRF guards, quotas/rate/deadline/concurrency/risk budgets, loop detection, human-in-the-loop approval, constitutional rules, action previews, honeytokens, audit/tracing, and Claude/OpenAI/Gemini/MCP tool-call integration.

Complete collection of battle-tested Claude Code configs — agents, skills, hooks, commands, and rules evolved over 10+ months of intensive daily use by an Anthropic hackathon winner

MCP server for monitoring dependency health across projects

pyobfus — the Python obfuscator. AST-based python-obfuscator / code-obfuscator with framework-aware presets (FastAPI, Django, Pydantic, Click, SQLAlchemy), reverse stack-trace mapping for AI-assisted debugging, and JSON CLI for Claude Code, Cursor, and MCP agents. Modern PyArmor alternative, Apache-2.0.

Model Context Protocol (MCP) server exposing Snyk via pysnyk

Transparent MCP proxy that watermarks agent tool responses and blocks data exfiltration caused by prompt injection.

Deterministic registry + integrity scanner for Model Context Protocol servers. Make MCP supply-chain boring.

MCP server for RugGuard — pre-trade rug-check API for AI agents. Wraps the x402 payment flow so Claude Desktop, Cursor, and other MCP-aware agents can call RugGuard without speaking x402 themselves.

A local gate for MCP traffic with cross-call memory for sensitive values.

MCP server for assistant-ui documentation and examples

n8n community node for Krova Cloud — create, sleep, wake, list, and delete Cubes (Firecracker microVMs) and read regions, images, and pricing via the Krova Cloud API.

No-code Claude Code hooks that forward raw lifecycle/tool events to a Radware LLM Protection ingest endpoint.

The MCP bridge that audits your routes before exposing them to LLMs — and blocks prompt-injection at runtime.

Dependency vulnerability monitoring MCP server — knows your lockfile, prioritizes by EPSS exploit probability, recommends fix versions.

Policy-controlled MCP server for agent-accessible services

SWT3 AI Witness SDK: cryptographic attestation for AI inference

Prompt quality analyzer — score, improve, and lint your AI prompts

OAuth and API Key authentication client for Lan Onasis MCP integration