- Conduid
- Marketplace
- #prompt-injection
MCP servers tagged prompt-injection
604 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.
Taintgate
π§ A policy gate for AI agent tool calls, with provenance tracking. Blocks what prompt-injection classifiers miss: where an instruction came from.
Bouncer
A deterministic exfiltration firewall for MCP tool calls β gates the destination, not the tool. No LLM in the decision path.
AgentGuard
Least-privilege policy gateway for MCP tool calls β injection blocking, secret redaction, hash-chained audit log
Runtape
Record AI agent runs locally and find which part of the context caused a decision.
JanusGate
The AI agent firewall: One face watches what enters, one watches what leaves. Defends against prompt injections, exfiltration, and scams with a multi-layer ensemble.
Countersign
Your AI agent writes its own 'allow this?' dialog, so it can hide what it's really doing. Countersign draws the dialog itself, so you approve the real command, and every yes becomβ¦
Sentinel
A runtime enforcement layer for agent payments β blocks injected or out-of-scope transactions before settlement. Signed mandate + provenance + tamper-evident receipt. EN/δΈζ, zero-β¦
Agentcheck
Scan AI coding-agent config files (CLAUDE.md, AGENTS.md, .cursor/rules, MCP configs) for hidden prompt-injection attacks.
Sheriff
Local-first security preflight for MCP client configs and AI agent tool setups.
Injection Guard
MCP server and CLI that scan untrusted content for prompt-injection patterns before it reaches your agent - offline, explainable, cross-agent.
Breaker
Replay-verified MCP security testing and deterministic policy hardening for tool-using AI agents
Eidolon
The cryptographic authority layer for AI agents. Watch every tool call live, delegate exactly the authority you choose, and kill it mid-session β enforced by a signed, revocable cβ¦
Agentpool MCP
A shared fix-pool for coding agents with a write-time poisoning shield β every post_solution is screened for prompt-injection and leaked secrets before it can reach a reading agenβ¦
Gaze
It sees the page, and it acts. Drive a real, already logged-in browser from the CLI or over MCP, with an enforceable approval gate. Chromium via CDP, Firefox via WebDriver BiDi.
Skillshield
π Security-scored directory for AI agent skills and MCP servers. 33,000+ scanned, 12% malware detection.
SafeInstall
Understand software before you run it β local-first static risk analysis for unfamiliar projects.
Tokenfuse
TokenFuse β runtime control for AI agents: per-run budgets, loop detection, burn forecast, kill-switch. Observability shows the fire; TokenFuse is the automatic extinguisher.
Hermes Shield
Input sanitizer for AI agents β anti-prompt-injection shield
Haechi
Experimental self-hosted AI context enforcement layer for LLM, MCP, vLLM, Ollama, and agent traffic.
RayCodes SkillSpector
π‘οΈ Streamlit dashboard wrapping NVIDIA SkillSpector CLI β scan AI agent skills, Claude MCP tools & Cursor extensions for prompt injection, data exfiltration & 64 vulnerability patβ¦
Maxion MCP
In-process security gate, prompt injection defense, and autonomous thermal governor for MCP AI agents.
Tool Sanitizer
Detect and neutralize Unicode concealment codepoints in MCP tool metadata (covert-channel control). AGPL-3.0-or-later.
OpenAgentShield
π‘οΈ Zero-Trust Security Firewall & AST Sandbox for Autonomous AI Agents & Model Context Protocol (MCP) Middleware
Fsck
Integrity check for MCP server configs audits Claude, Cursor, VS Code and Windsurf agent configs for secrets, injection-prone args, tool poisoning and dangerous capability combos.
Local AI Agent
AgentTrail is a local-first AI agent layer for Ollama/local models that shows its work: semantic search, diff-safe edits, receipts, replay, memory, MCP, reports, and trust controlβ¦
Skillguard
Static security scanner for AI agent skills and plugins β flags prompt injection, hidden Unicode, exfiltration, and dangerous commands in SKILL.md/CLAUDE.md and scripts.
Fluiq SDK
Instrument any LLM app in 2 lines. Tracing, evaluation, security, and caching for OpenAI, Anthropic, Gemini, LangChain, MCP, and more.
Agentic Workflow Guard
Static analysis for AI automation workflows. Find prompt-injection paths, overpowered tools, and write-capable agent jobs before they run.
ZugaShield
7-layer AI agent security system β stop prompt injection, data exfiltration, and AI-specific attacks in under 15ms. Zero dependencies.
Mylonite
Open-source AI-layer security testing β probes your AI agent for weaknesses and writes a validated regression test for each one it finds, gating CI.
Agent Skill Scan Action
GitHub Action: Scan agent skill files for security vulnerabilities. 22 rules across prompt injection, capability escalation, data exfiltration, encoded payloads, and composition rβ¦
Attenu Guard Ts
Attenu Guard for TypeScript β per-agent permissions on every tool call and sub-agent handoff (a sub-agent never holds more than its parent) with a hash-chained audit log verifiedβ¦
Skillguard CLI
Static security scanner for AI skills, agents, prompts, and MCP instruction files
LLM Security Skills
Agent Skills that turn your AI coding agent into an LLM security reviewer β prompt-injection testing, OWASP LLM Top 10 audits, MCP & RAG review, KVKK/PII checks. English + Turkish.
Trustline
Trusted baseline + auto-rollback for AI agent config files (.claude/, AGENTS.md, .mcp.json). Detects prompt-injection / supply-chain tampering and rolls back to a trusted snapshotβ¦
Ctxsentry
Scan a repository for prompt-injection payloads before you point an AI coding agent at it.
Bedvibe Mail Bridge
Local Windows desktop app + MCP bridge that lets Claude Code/Codex safely assist with Gmail - read, cleanup plans, drafts, and RFC 8058 one-click unsubscribe - every destructive aβ¦
Mcpbait
Red teaming framework that proves whether an MCP-speaking agent can be hijacked by a malicious server
Skillfence
Runtime behavioral security for Agentic Skills β deterministic policy engine, human-in-the-loop gate, full OWASP Agentic Skills Top 10 (AST01βAST10) coverage. Not another SKILL.mdβ¦
Agent Chaperone
Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.
Gauntlet
A CI linter for what your MCP server publishes: tool poisoning and prompt injection across every surface an agent sees, definition drift between runs, and schema rot.
Atr
Rust loader and matcher for Agent Threat Rules YAML. Vendors the upstream ATR ruleset (MIT, ATR Contributors).
Ozm Codex Agent Governance Skills
Codex-native OZM skill pack for AI coding agent governance, agentic coding loops, claim ceilings, and AGENTS.md-aware workflows.
AntiClaude
Open-source red-teaming toolkit for AI agents. 64 attack payloads covering 7/10 OWASP Agentic Top 10.
Skill Vet
Vet AI agent skills (SKILL.md, MCP bundles, Cursor rules) before your agent runs them. Prompt injection, exfil, cred harvesting β zero deps, one file.
Is This Safe
Trust in AI agent tooling is a chicken-and-egg problem. Start here β audit a skill repo before you install it.
Cunning Claw
Y dyn hysbys β a local-first AI butler that owns the glass and the hands. Sees your screen, runs your shell, speaks at dawn in Welsh, and asks a human before consequences. Built iβ¦
Skillxray
Scan an AI agent skill for prompt injection, hidden Unicode, dangerous commands, and leaked secrets before you install it.
Mia
Managed Identity for Agents. Scoped, revocable, live-checked identity and enforcement for AI agents acting on behalf of a human.
Skilltest
SkillTest: test framework and CI gate for AI agent skills (SKILL.md) β the engine behind skillemall.ai