Search

DevSecOps toolkit for AI-assisted secure development — security scanner, ISMS dashboard, asset management

Production-grade Security Model Context Protocol (MCP) platform for static, dependency, secret, configuration, mobile, and live security audits.

EP-MCP middleware (reference implementation). Wraps an MCP tool-call handler: irreversible tool calls route through consent → Class-A signoff → an emitted EP-RECEIPT-v1 + an appended provenance entry; everything else passes through. Includes the demand ho

Portable, model-agnostic cybersecurity sub-agent exposed via MCP, CLI, and Python API.

Kernel-level governance MCP server for AI agents — enforces deterministic policies (tool filtering, budget caps, rate limits, audit logging) instead of prompt-based guardrails. Part of microsoft/agent-lightning (14k★). Run via `npx agentos-mcp-server`.

Fleet-scale discovery and audit of MCP servers and agentic AI tooling across an endpoint fleet.

A deterministic layer between untrusted content and agent actions: it removes the hidden layer, remembers where data came from, and keeps calls inside the boundaries of the intent.

Open-source behavioral sandbox for Model Context Protocol (MCP) servers

Non-custodial burner wallet for AI agents: make a wallet, check balance, send, swap.

MCP server that points an AI agent at a LIVE URL and confirms which secret files are publicly served — exposed .git, .env, JS source maps, backup/SQL dumps, directory listing and dotfiles — by fetching the bytes, not a checklist. Zero deps, read-only.

Model Context Protocol (MCP) server for the A2A (Agent2Agent) protocol compliance test kit. Lets Claude Desktop, Cursor, Codex, and other MCP clients invoke run_compliance / validate_agent_card / list_checks / explain_check / ssrf_check_url as native tool

Pre-tool policy enforcement + JSONL audit for AI agents. Apache 2.0.

📇 ☁️ 🏠 🍎 🪟 🐧 - Your complete Slack context for Claude—DMs, channels, threads, search. No OAuth apps, no admin approval. `--setup` and done, 11 tools, auto-refresh.

The firewall for MCP tool calls. Block, audit, replay with evidence bundles.

AntiClaude core engine: agent red-team evals, report compare, local guard, and runtime policy

Bun-native MCP stdio bridge for the Burp MCP extension

Node wrapper for the Armorer Guard local Rust scanner and MCP proxy.

Local PII and secret redaction for Python LLM apps, AI agents, tool calls, and MCP

MCP server for Cyberismo content projects

AI Agent 付款安全层: 身份/意图/密钥 三道信任支柱 + 四道闸门。给 AI 定义带消费上限的数字身份, 防提示注入, 密钥不落盘。Python + MCP