“MCP and agent security”

MCP security hardening — credential leakage prevention, input sanitization, and tool access control.

AI 与 MCP 安全评估 — Prompt 注入、工具滥用、MCP 信任边界、Agent 权限逃逸、数据泄露、模型风险、GAARM 风险矩阵。Use when testing LLM-based applications, MCP servers, agent orchestration systems, AI…

Secure AI agents against prompt injection, tool abuse, and data exfiltration with defense-in-depth controls.

Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.

MCP security trust-check for agents before installing MCPs, Skills or tools.

AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.

Self-hosted Go workspace where AI agents run security tools through MCP for authorized testing.

Open-source computer use agent from Simular that operates desktop and web apps by clicking, typing and scrolling.

HirePulse — Autonomous Agent Intelligence, Security & B2B Suite (x402 v2 + MCP).

AGENTS.md from MobSF/Mobile-Security-Framework-MobSF: 245 lines covering Code Quality — Mandatory Before Every Commit, Security Architecture, Past…

Subagent "security-auditor" from ruvnet/ruflo: Security audit and hardening specialist

Subagent "security-analyzer" from nrwl/nx: Use this agent during PR review to hunt injection-class vulnerabilities in a PR's changes - command injection…

CLI that discovers agent components on a machine and scans MCP servers and skills for prompt injections.

Enterprise platform for AI asset discovery, red teaming and runtime security across agentic workflows and MCP.

Agent security and governance platform that controls agent behavior at runtime across endpoint, SaaS and cloud.

AI Agent Security Scanner for IDEs

Cisco-AI

Scan MCP servers, agent skills, and AI-generated code for prompt injection, data exfiltration, and supply chain threats.

DeepSweep: AI Agent Security & Code Review

deepsweep-ai

Security review for AI coding agents: AI agent security, vulnerability detection and secrets review, locally.

SDLC Agents 4 Enterprise

dnguyenminh

Multi-agent SDLC pipeline for enterprise — 9 AI agents (SM, BA, TA, SA, QA, DEV, DevOps, Security, UI) orchestrated via MCP

Identity security for AI agents and non-human identities, covering discovery, access and remediation

Observe, enforce and build identity controls into AI agents, with runtime policy checks before agent actions run.

Ping Identity offering for securing AI agents, MCP servers and agentic platforms with identity governance.

Python framework for MCP-based agents with composable workflow patterns, MCP server creation and Temporal-backed durable execution.

Python library for autonomous agents that run scheduled tasks and exchange messages on the Fetch.ai network.

Python toolkit for signed identities, verifiable credentials and delegated authority for AI agents, with MCP and REST interfaces.

Workflow platform where any team can build automations and AI agents while IT and security keep visibility and control over them

Visual builder for automations and AI agents that connects 3,500+ apps and AI models, with an MCP server and custom JavaScript or Python code

Enterprise platform for building and running AI agents called Genies, with a low-code Agent Studio and 1,200+ app connections

Open source gateway for HTTP, gRPC, LLM, MCP and agent-to-agent traffic in one data plane.

Platform for deploying apps and AI agents, with an AI Gateway, sandboxes and fluid compute.

AI gateway capabilities in Azure API Management to secure, scale, monitor and govern AI backends.