- 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.
Draw Io MCP
A local, Docker-ready MCP server that creates and edits native, editable .drawio XML.
Redteam
MCP server security testing with live adversarial checks, a reproducible demo, HTML reports, and a GitHub Action.
Srv
Containerized service for 1mcp MCP aggregator gateway behind Traefik with TLS/SSL
MCPShield
Local security scanner, hardening checks and optional stdio policy guard for Model Context Protocol (MCP) servers. Source beta by Nullvora.
Sentinelmcp
The EDR for MCP servers — 100% local, read-only. Discover, fingerprint and monitor every MCP server your AI agents expose across 14 clients; catch rug-pulls, tool poisoning, typos…
Golf Scanner
Discover and audit MCP servers for security vulnerabilities across Claude Code, Cursor, VS Code, and more
Golf Testing
Comprehensive MCP testing framework - test performance, security and compliance in one CLI
Solesonic MCP Server
An enterprise-grade MCP server with built-in federated identity support for SSO across providers and secure, scalable access management.
Lokis MCP
Lokis MCP Server will trick your LLM
Cve Project
The Project shares all information on MCP related CVE's published
Authserver
OAuth 2.1 Authorization Server for the Model Context Protocol (MCP)
Firmis Scanner
AI agent runtime security scanner - detect malicious behavior in Claude Skills, MCP Servers, Codex Plugins, and more
Fronesis-Labs/dcl-webhook
call via x402 (USDC on Base), from $0.01. `mcp.fronesislabs.com/mcp`
IntentProbe
Activation-probe security scanner for AI agent tooling. Reads a model's internal activations to detect poisoned MCP servers, skills, and packages before install.
Foundgine
Foundgine is a semantic execution runtime for .NET. It lets applications expose capabilities as structured intent rather than exposing persistence APIs directly, then resolves aut…
AgentNull
AgentNull: AI System Security Threat Catalog + Proof-of-Concepts. Collection of PoCs for using Agents, MCP, and RAG in bad ways.
Marshal MCP
Mcp services by marshal
NebulaFinger
MCP_NebulaFinger使AI具有WEB和服务指纹识别能力
Security 101
The Model Context Protocol (MCP) represents a significant advancement in AI system integration, but with it comes a new landscape of security challenges. This repository provides…
Arthur MCP
No code system to provide MCP Server using Any Data Source
Opshaven
A least-privilege MCP server for safe, structured VPS inspection and controlled operations over SSH.
In Practice Anthropic Course
This repo is based on the MCP course by Anthropic and extended with my own implementations, patterns, and learnings.
PowerShellGuardian
Secure AI bridge for Windows PowerShell automation using MCP communication and controlled local execution.
Depsdevmcp
MCP for deps dev
Oauth Authentication
My notes and learnings while implementing MCP OAuth authentication, JWT verification, authorization, and protected MCP servers.
ZTA MCP Server
Zero Trust Agentic Access based MCP Server Reference Implementation
Aran MCP
Enterprise-Grade MCP (Model Context Protocol) Security and Management Platform
Inject
High-performance MCP (Model Context Protocol) injection scanner featuring 2,338+ payloads, 70+ wordlists, advanced evasion techniques, multi-transport fuzzing, and automated vulne…
Seshat App
Local MCP proxy that governs what AI agents do on your machine. Policy enforcement, audit receipts, hash-chained provenance.
Agent Trust Preflight
Free MCP + AI agent trust preflight: 20 practical checks, safe examples, VS Code tooling, drift review and authority analysis.
Enterprise Readiness
Open MCP security, identity, provenance and enterprise-readiness guidance — with practical checks for servers, tools and agent-facing infrastructure.
SCML
Production middleware for securing agentic AI systems. Enforces least-agency policy, scans for prompt injection, gates tool calls, and logs every decision to a tamper-evident SHA-…
Eczid MCP Security Toolkit
Free MCP security checks, examples and developer tools for understanding MCP configuration, tool exposure, change and runtime trust posture.
Sunglasses
Sunglasses for AI agents. Protection layer + neighborhood watch.
Suprawall MCP Plugin
Official SupraWall MCP (Model Context Protocol) Security Plugin. Enforces deterministic guardrails, least-privilege tool access, and PII interception for AI agents.
Overstep
Authorization testing for REST APIs and MCP servers. Declare who may do what as a matrix, and overstep turns it into positive and negative tests that catch BOLA, BFLA, BOPLA and p…
SkillGate
Pre-merge and pre-install trust checks for AI-agent skills and MCP configurations. Scan capabilities, detect risky changes, and block unapproved agent behavior in CI.
Deconvolute Demo
Live PoC: MCP attacks that compromise AI agents mid-session and how to block them in a few lines of code.
FrostMI
Local-first macOS intelligence for AI Agents: MCP and Skill discovery, process attribution, FSEvents, network destinations, Session Graphs, and local evidence.
Nightward
Local-first TUI for auditing AI agent state, MCP config, and dotfiles backup safety
Mcpnuke
MCP red teaming & security scanner — enumerate, probe, and exploit Model Context Protocol servers
Mcpkernel
The Security Kernel for AI Agents — MCP/A2A gateway with policy enforcement, taint tracking, sandboxed execution, deterministic envelopes, and Sigstore audit. OWASP ASI 2026 compl…
Attestral
Open-source security scanner for MCP servers and AI agents: finds prompt injection, tool poisoning, and excessive agency, and models the cloud your agents can reach. pip install a…
Unified MCP Core Starter
An Java framework that turns your Spring Boot application into a fully compliant Model Context Protocol server for seamless LLM integration.
Injection Lint
Semantic prompt-injection & tool-poisoning linter for MCP servers. Precision-first, 100% local — tells real injection apart from legitimate tool descriptions.
Fulcrum Boundary
The action boundary for routed agent tools. See what your AI tools can do; block what they should not.
Security Evidence Redactor
Dependency-free JSON findings summary that emits severity counts without copying finding details.
Audit Scanner
Read-only AST security scanner for Python Model Context Protocol servers before connecting them to AI clients.
Cadre Video Editor Plugin
Official MIT-licensed Cadre editing skill and Claude plugin for local MCP-controlled macOS screen recording and video editing.
Ccs Integrations
Framework-native adapters for CCS (Correctover Conformance Shape) cryptographically signed runtime receipts — Ed25519 + JCS signed audit evidence for AI agent tool calls (Pydantic…