Search

Local, safety-first MCP server for Rapid7 InsightConnect / Automation

Finds what your AI agent's tools can be tricked into doing — then proves it by running the exploit in a sandbox. MCP, Vercel AI SDK, LangChain, Mastra.

MCP server for the Guard ecosystem — config validation, docs search and live threat detection for fastapi-guard, guard-core and guard-agent.

FedRAMP boundary visualizer & OSCAL-format SSP/POAM generator

OWASP-aligned adversarial red-team harness for LangGraph, CrewAI, and MCP agents.

Neutralise prompt-injection / tool-poisoning in untrusted MCP/LLM tool text before it reaches the system prompt.

MCP Server for dependfix: expose scan/fix capabilities to AI assistants

Scans any wallet for dangerous ERC-20/721/1155 token approvals and infinite allowances, scoring drainer exposure and emitting revoke transactions.

OAuth 2.1 Authorization Server for the Model Context Protocol (MCP)

Multi-framework threat intelligence MCP server — STRIDE, DREAD, LINDDUN, and PASTA analysis for AI coding agents

Temporary package placeholder for staged publishing

VibeSecurity — Auditoria de segurança para quem cria com IA. Secrets, vulnerabilidades e rotas sem auth.

ghidraMCP enables LLMs to autonomously reverse engineer applications by integrating Ghidra's decompilation and analysis tools with MCP clients.

Read-only MCP server + live panel to detect & explain endpoint monitoring (EDR/DLP/MDM) on macOS, with first-class coverage of Chinese enterprise agents.

AEGIS MCP server — exposes scan / findings / score / compliance / fix-suggestion tools to any Model Context Protocol agent (Claude Code, Cursor, Continue, Zed). Five registered tools: aegis_scan, aegis_findings, aegis_score, aegis_compliance, aegis_fix_su

MCP server for the Check Point Harmony Email & Collaboration API

A safety floor your AI agents can't get under: one policy for Claude Code, Codex, Gemini CLI, Cursor, Windsurf and MCP, checked before every tool call, with a tamper-evident ledger. Try: npx provio scan

[](https://glama.ai/mcp/servers/nickgeorgeseo/mcp-gatehouse) 🐍 🏠 - Permission tiers, approval gates, and secret-redacting audit logging enforced inside the server at the tool boundary; includes a demo order-desk server. `uvx mcp-gatehouse`

Kill switch and tripwires for AI agents: honeytokens, decoy files, decoy MCP tools and action budgets trip a sticky fuse that stops the agent, whether or not any detector saw the injection. Claude Code hook + Python library. The CONTAIN leg of the bastion family.

tsk is a local MCP server that sits between your AI agent and external APIs. It holds your credentials, enforces per-tool call rules, scrubs sensitive data from API responses before they reach the model's context, and keeps a queryable local log of everything your agent actually did.