- Conduid
- Marketplace
- #prompt-injection
MCP servers tagged prompt-injection
63 live MCP servers tagged "prompt-injection", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with prompt-injection.
Awesome MCP Security
Security scores for 800+ MCP servers. 9 analyzers scan for prompt injection, toxic flows, and attack surface risks. Updated daily. 🛡️
Security Checklist
MCP is being adopted rapidly. Security guidance is lagging behind. This checklist gives security engineers, platform teams, and technical leaders a clear, actionable baseline for…
mcp-guardian
MCP security scanner - detect prompt injection in tool descriptions
Aguara
MCP server that gives AI agents a local security scanner before they install or trust third-party tools.
Pic Standard
Open standard for Provenance & Intent Contracts (PIC) in AI agents. Verify intent, provenance, and evidence before high-impact tool calls.
Agent Opfor
Open-source adversary emulation for AI agents and MCP servers.
Agentseal
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resistance, and audit live MCP serv…
Secure Claude Code
Security guardrails for Claude Code, MCP tools, and Claude cowork workflows. Local-first modular YARA-style guard packs for secrets, exfiltration, prompt injection, MCP abuse, and…
Sponsio
Deterministic safety solutions for probabilistic AI agents
Adrian
Runtime security monitoring and control for AI agents. Catches malicious tool use, prompt injection, and policy drift in real time, before the agent acts.
Prismor
Runtime security for Agents. Blocks dangerous commands, prevent secret leaks, stop prompt injection, gate risky package installs and visibility and control over tool calls.
Www Project Agent Memory Guard
OWASP Foundation web repository
Panguard MCP Proxy
MCP Proxy — runtime interception for AI agent tool calls using ATR rules
fr0gger/MCP_Security
AICLUDE Security Vulnerability Scanner - MCP Server for querying vulnerability scan results
Veritensor
The Anti-Virus for AI Artifacts & RAG Firewall. A static analysis tool scanning Models and Notebooks for RCE, Datasets and RAG docs for Data Poisoning, PII, and Prompt Injections.…
Mcptrustchecker
MCP security scanner — offline, deterministic A–F Trust Score for Model Context Protocol servers. Detects tool poisoning, prompt injection & toxic flows.
Clawseccheck
🦞 Local, read-only security scanner for OpenClaw. Finds config, prompt-injection and supply-chain risks — A–F grade.
Openclaw Superpowers
44 plug-and-play skills for OpenClaw — self-modifying AI agent with cron scheduling, security guardrails, persistent memory, knowledge graphs, and MCP health monitoring. Your agen…
Avakill
🔪 Open-source safety firewall for AI agents. Intercepts tool calls before they execute, enforces YAML policies, and kills dangerous operations in real-time. Works with OpenAI, Ant…
AegisGate
Open-source security gateway for LLM APIs — prompt injection detection, PII redaction, dangerous response sanitization, and audit logging. OpenAI/Claude compatible, MCP & Agent…
Openclaw Security Guard
Complete security layer for OpenClaw - CLI Scanner + Live Dashboard. Secrets detection, config hardening, prompt injection scanning, MCP server auditing. Zero telemetry.
Signature Cloaking
This research introduces MCP Signature Cloaking - a novel backdoor technique that allows attackers to exploit hidden parameters in MCP servers, concealing malicious behavior behin…
Canary
Deterministic, read-only static auditor for GGUF models: behavioral chat-template backdoors + SSTI, tokenizer, config, and model-card surfaces - never renders, never loads weights…
Fence
Local-first security scanner, MCP protocol inspector, dynamic fuzzer, Docker sandbox, and report generator for Model Context Protocol servers.
ShibaClaw
🐾 A loyal, self-hosted AI assistant framework. Multi-channel (Telegram, Discord, Slack…), parallel agents, MCP support, WebUI with OAuth, and hardened against prompt injection
Aigis
Deterministic, zero-dependency Python firewall for AI agents — MCP rug-pull, memory poisoning, indirect injection, exfil channels. 44 compliance templates (US/CN/JP/EU).
SecureAI Scan
SecureAI-Scan is a CLI tool that scans TypeScript and JavaScript codebases for security issues specific to AI-powered apps — prompt injection, MCP tool abuse, RAG data poisoning,…
Cyvisguard
Security control plane for AI agents — identity and delegation, capability policy, data-flow taint and a live audit trail, enforced over MCP. Guards a real Claude Code end to end.
ADR
ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.
Modelfuzz
🛡️ Runtime guardrails for AI agents. Intercept and block unsafe tool calls caused by prompt injection.
Airlock Bot
Permissions-aware MCP gateway with human-in-the-loop approval for AI agents
Tooltrust
MCP server that scans other MCP servers for prompt injection, data exfiltration, and privilege escalation. Add to your .mcp.json and let your AI agent audit its own tools.
Skillsafe
SafeSkill CLI — scan AI tool skills for security risks and prompt injection
Agentaudit
Security scanner for AI agent packages — CLI + MCP server
Decoy Scan
Security scanner for MCP server configurations. Finds risky tools, vulnerable packages, and suspicious servers across Claude Desktop, Cursor, VS Code, and more.
Mcpguard
Security scanner for MCP servers — detect tool poisoning, malicious code patterns, and supply-chain risks before your AI agents execute them.
Demipass
Secrets management for LLM sessions. Keep credentials out of context windows.
Rea
Agentic governance layer for Claude Code — policy enforcement, hook-based safety gates, audit logging, and Codex-integrated adversarial review for AI-assisted projects
Vex
A transparent MCP security proxy: inspects tool descriptions for injection, pins tool definitions to detect rug-pulls, enforces a default-deny capability policy, and writes a tamp…
Mcpsense
Security scanner for MCP servers. ESLint + Snyk for the Model Context Protocol.
Server Engine
MCP server framework with Express, middleware pipeline, and tool orchestration
Tokesave
The ultimate AI token-saving MCP middleware — compression, caching, injection shield, multi-server routing, and more.
Warden Gateway
Warden — an open-source MCP gateway. A control plane for AI tool access: security screening and observability for Model Context Protocol servers.
Risk
Audit MCP configs and servers for risky tools, secret exposure, and prompt-injection patterns.
Sealpin
A supply-chain and prompt-injection scanner for MCP (Model Context Protocol) servers.
Nominee
Decision-bound Model Context Protocol tool handlers for governed AI agents
Agent Config Audit
Security auditor for AI agent configurations — scans MCP servers, Claude Code settings, agents, skills and hooks for risky permissions, inline secrets, unpinned supply chains and…
Mcpie
Security scanner for MCP servers. Think `npm audit` for the Model Context Protocol.
Prompt Injection MCP
MCP Server for authorized AI security research and penetration testing (Educational purposes only - requires explicit authorization)
joergmichno/clawguard-mcp
Security scanner for AI agents that detects prompt injections using 42+ regex patterns