- Conduid
- Marketplace
- #mcp-security
MCP servers tagged mcp-security
248 live MCP servers tagged "mcp-security", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with mcp-security.
AgentInterdict
AgentInterdict — runtime enforcement for autonomous AI agents. Trust context. Verify authority. Interdict unsafe action.
Velvet Rope
Test whether blocking one AI-agent route actually prevents the real-world effect. ShadowPath maps and replays alternate authorization paths.
Wardrail
Local security scanner for vibe-coded apps: stop API key leaks, Git-history secrets, and unsafe MCP or AI agent instructions before commit.
Sec Scanner
Comprehensive security scanner for Model Context Protocol (MCP) servers
Autonomous Docs MCP
Claude Code MCP Tool! Why Pay for Automated Documentation?
ZTeasy
Zero Trust Gateway architectural MVP, used to demonstrate Claude Code capabilities in creating complex solutions.
Agentcapdiff
AI agent security policy-as-code for detecting capability, permission, and least-privilege changes across MCP, OpenAI, Claude, LangChain, LangGraph, and CrewAI tools.
Fourgate Site
Checks your MCP connector before a user finds out it's broken.
Dsh MCP Security
dsh-mcp-security
Awesome AI Agent Security
A curated, opinionated list of resources for securing AI agents, LLMs, and the Model Context Protocol (MCP) — attacks, defenses, tools, labs, and research. All links verified.
A555mcp
:peach::robot: A 555 MCP security playground
Agentward
Audit what your AI agents can actually do to your machine. Scans installed MCP servers, skills, hooks and agent configs for leaked credentials, hidden prompt injection, exfiltrati…
Pontifex
Build Enterprise-grade MCP servers
Tier1 Gate
Tier-1 Pre-Task Gate plugin for OpenClaw — mechanically enforces pre-task lesson checks via before_tool_call hook. Supports MemPalace, local docs, and online handbook lookups.
Langchain Course Modified
An 8-stage architectural benchmark exploring enterprise agentic AI patterns—from schema-enforced tool execution and local/cloud LCEL runtimes to stateful LangGraph loops, self-cor…
Intentguard
IntentGuard is a predictive runtime security framework that correlates AI agent behavior across multiple MCP servers to forecast attack campaigns before any individual action appe…
Investigation Reports
MCP security investigation and hunting reports — reference material for detecting and investigating agent tool activity.
Fastest Domain Name Search MCP
The Fastest Domain Name Search is provided by Domainnameregistration.com. This MCP lets agents check up to 1,000 domains in one MCP request and distinguish available, registered,…
Lunar Gatekeeper Sentinel
Lunar Gateway 2026: Agent-Native MCP Security & Governance Hub for AI Workloads
Deconvolute
Policy-as-code enforcement and observability for MCP tool calls. Wraps AI agent sessions with cryptographic integrity checks, argument-level CEL policies, and a full audit trail.
Spring AI Integration
A curated collection of Spring Boot projects demonstrating AI and LLM integrations, including examples of AI-powered applications, multi-provider LLM setups, and best practices fo…
Universal AI Hub
— or your Universal MCP Hub (Sandboxed) — or a secure All-In-One AI wrapper with dual interface: REST + MCP aka: a clean, secure starting point for your own projects. Pick the de…
Xclaude Gateway
Durable local audit trail for Claude Code and MCP tool activity. Records, classifies and keeps the history on your Mac.
Magus Opensecmcp
A deterministic execution firewall for MCP agents. Local-first, open source, no LLM judging the thing it's meant to secure, no cloud dependency, no telemetry leaving your machine…
Halflist
CI-first conformance testing and benchmarking CLI for MCP servers. Lint your MCP server before your users do.
Sentinel Scan Vscode
VS Code extension: inline MCP config security diagnostics (mcp.json / claude_desktop_config.json), free, powered by sentinel-scan-cli's OWASP-mapped heuristics
Vulnerability Detection
Self-contained MCP security server that scores AI agent tool-calls with a rule-based library + behavioral detector, giving explainable, MITRE-mapped verdicts for known attacks
Agentops Watchtower
Local-first AgentOps flight recorder and capability firewall for MCP-based coding agents with OpenTelemetry traces.
Correctover Scan
Security scanner for MCP servers and AI agents — detects credential leaks, RCE, SSRF and missing auth against OWASP AISVS 1.0; also scans published JS bundles/npm packages.
MCPGoat
Deliberately vulnerable MCP server (aka MCP Goat) for security training — 26 challenges across 4 difficulty levels (incl. a secure reference), a victim-agent harness, and one-comm…
Contextguard
Zero-trust governance middleware for Model Context Protocol deployments
AegisAgent
Zero-trust API firewall and security integrity layer for autonomous AI agents & Model Context Protocol (MCP) tool execution. Secure, TOCTOU-proof, fail-closed.
Yang Promptlab
AI security testing — find security vulnerabilities in LLM apps, chatbots, AI agents, MCP servers, and RAG systems. Mapped to OWASP (LLM, Agentic, MCP) and NIST AI RMF.
Sentnelops Node
Node.js SDK for SentnelOps — MCP firewall, agent identity, runtime policy, and audit evidence for AI agents
Supersayan Webmcp
⛨ Next-Generation WebMCP Security Intelligence Platform. Detect. Defend. Trace. The complete countermeasure suite for the agentic web. Includes an experimental Google Chrome secur…
Saferico CLI
Solidity security scanning with 201 detectors that run on your machine. CLI + local MCP server.
Eczid MCP Readiness
Practical MCP readiness, security and stateless-migration resources for teams moving MCP servers toward enterprise deployment.
Agent Sec Scanners
Security scanners for AI workloads on one shared audit engine. Home of bedrock-security-mcp (AWS Bedrock auditor, MCP + CLI) and @miaggy/core. Findings map to OWASP LLM Top 10, OW…
Chaperone
Open-source AI agent security gate: deterministic ALLOW/BLOCK/ESCALATE authorization before every tool call, plain-English policy compilation, tamper-evident audit ledger. MCP sec…
Risk Inventory
Dependency-free MCP configuration risk inventory CLI and GitHub Action
Job Assistant
An MCP server built with Python and FastMCP that connects an AI host: claude-code to your own Google Drive and Gmail, to reduce the manual copy-pasting involved in job hunting whi…
epistemedeus/skillguard
y github:epistemedeus/skillguard mcp`
Tool Calling
A runnable demo using an MCP server demonstrating secure MCP best practices with a refund_order tool that moves money.
Toolproof
Trust grades, capability lockfiles, and signed evidence for the AI tool supply chain. Scan any MCP server or API before your agent connects. Paid by nobody we scan.
Starter Demo
Runnable TypeScript MCP server demo with tested tools, official SDK protocol proof, and CI.
SkillWatch
Independent, local-only watcher for the AI-skill supply chain: flags bait-and-switch changes in the pages skills and MCP tools reference. Sends nothing anywhere. Python CLI.
Security Docker Gateway
Vulnerable MCP server + layered defenses (static scan, runtime interceptor, Docker MCP Gateway).
Loopback Litmus
Safe browser-to-localhost security checks for local AI agent and MCP control planes.
Literal Deterministic MCP Harness Protocol
Predictable tool decision and execution, compacted schema prompts, auditability, observility, normalization, generalization, local and private by design.
Kimi Code Security Hook
PreToolUse security gate for Kimi Code: blocks secret exposure & SSRF before WriteFile/Shell via correctover-scan (MCP config security)