- Conduid
- Marketplace
- #llm-security
MCP servers tagged llm-security
557 live MCP servers tagged "llm-security", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with llm-security.
Warden
Security scanner for MCP server configs. Finds leaked API keys, unpinned npx/uvx/docker servers, typosquats, malicious packages and tool poisoning in Claude, Cursor, VS Code, Wind…
Sift
Scans AI agent instruction files (CLAUDE.md, .cursorrules, mcp.json) for hidden or planted instructions
Sentinelmcp
Stateless enterprise policy firewall & token-cost proxy for Model Context Protocol (MCP).
Portcullis
A policy-enforcing gateway for the Model Context Protocol. Aggregates MCP servers, enforces tool-call policy, scans results for prompt injection and leaked credentials, and audits…
Prompt Injection MCP
MCP Server for authorized AI security research and penetration testing (Educational purposes only - requires explicit authorization)
Ovogo
Ovogo: Autonomous Red Team Coordination Engine. 基于 AI Agent 的自动化渗透测试与红队协同引擎（专为靶场环境设计），支持 MITRE ATT&CK 攻击链生成、多节点并行利用与 Flag 自动化收集。
9hannahnine-jpg/arc-gate-mcp
Runtime governance for MCP tool calls. Blocks prompt injection and capability abuse before tool results reach your agent.
ppcvote/misp-mcp-server
intel tools (events, attributes, search, tags, feeds, galaxies). Scans every MISP response for adversarial seeding before returning to LLM. Tracks [MISP/MISP#10745](https://github…
Aiguard
Portable, Rust-powered security harness for CLI coding agents. Blocks prompt injection, redacts secrets, pins MCP servers, audits every tool call.
MarketNow MCP
Free trust layer for AI agents using MCP: verify credentials (8 formats), scam-check domains, fingerprint tools. Remote endpoint: https://www.marketnow.site/api/mcp — 100% free, n…
faizbawa/mcp-remote-ssh
ssh`
Firmis Scanner
AI agent runtime security scanner - detect malicious behavior in Claude Skills, MCP Servers, Codex Plugins, and more
Warrant
Verifiable constraint enforcement for AI agents - signed warrants, Merkle constraint commitments, tamper-evident audit logs, and collusion-aware multi-agent auditing. Rust core +…
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.
MCPBoundary
A local proxy that wraps your MCP servers and checks each tool call against policy and live state before it runs - allow, block, or request a refresh, with a reason the agent can…
Toolfence Site
MCP security scanner — Toolfence scans any Model Context Protocol server and reports the risks your AI agents inherit: tool poisoning, prompt injection, tool drift, over-broad sco…
Customhouse
Deterministic MCP proxy that blocks money-moving and data-egress tool calls in any agent session that has received untrusted content. No model in the decision path.
Aegir
MCP's during the inception of this project lack security controls, this project seeks to address this, implementing a defence in depth approach as a proxy between your MCP server…
CyberScanAI
AI Agent Tool for Penetration Testing and Network Forensics
Stress Test
Red team toolkit for stress-testing MCP security scanners — find detection gaps before attackers do
Shark Security Lab
Reference MCP security lab: toxic tool metadata, multi-server mcp.json harness for static scan, localhost AAuth fixtures, YARA (OWASP Agentic ASI01–ASI10). Stress-test MCPShark an…
Mcpharden
MCP server hardening linter — capability declarations, transport, tool descriptions
Sentinelagent Guard
A protocol-native, open-source firewall for MCP servers and AI agents — blocks tool poisoning, rug pulls & data exfiltration. Deterministic, no LLM in the path. Apache-2.0.
Trustshell
Open-source toolkit for AI agent security — autonomous attacker + static engine + scanner + red-team skills. Exploit-validated. trust-shell.com
Dcl Skills
Security & compliance skills for AI agents (jailbreak defense, PII/secret redaction, hallucination checks) with a DeFi-specialized suite — free instruction-only mode or paid on-ch…
Zn
Zero-trust, bidirectional prompt injection & tool-poisoning security gate for AI agents.
Ctrlrun
The execution safety layer for AI agents.
Saltcode
Give your coding assistant security super powers with Salt Code. Secure code with every prompt and a much quieter security team.
Csc Agent Guard V1
Deterministic pre-execution safety gate for AI agents: verify tool calls against trusted evidence, policies, and WorldState before side effects.
AI Agent Launch Tools
Dependency-free launch hygiene tools for AI agent and MCP builders
Aicard
Auto-generated NIST AI RMF / EU AI Act Annex IV model & system cards
Issa
Issa — Intelligence Server-Side Agent. Issa: An open-source Action-Control Gateway to stop AI agents from executing unauthorized side-effects.
Shrike
The autonomous security agent for your AI stack — finds the vulns in your MCP servers & agent tools AND writes the fixes, on a local model.
Sunglasses
Sunglasses for AI agents. Protection layer + neighborhood watch.
Agent Guardrails Spring Boot Starter
Security & governance guardrails for MCP agents in Java — audit trail, agent-to-tool authorization, prompt-injection detection and rate limiting as a zero-config Spring Boot start…
Deconvolute Demo
Live PoC: MCP attacks that compromise AI agents mid-session and how to block them in a few lines of code.
Project Guardian
AI Guardian Firewall — a local, user-space, agent-agnostic firewall that mediates an autonomous AI agent's actions (files, shell, network, services) with a deterministic policy bo…
AegisForge MCP
Zero-trust AI security research engine built on MCP, Tauri v2, and Rust — with prompt injection defense and sandboxed tool execution
Security Patterns
MCP security patterns — 10 production implementations mapped to OWASP MCP Top 10. Prompt injection, credential isolation, HITL governance, session recording. Working attack demos…
Imara
Runtime governance for AI agents: audit trails, policy enforcement, and compliance for MCP tool calls
FrostMI
Local-first macOS intelligence for AI Agents: MCP and Skill discovery, process attribution, FSEvents, network destinations, Session Graphs, and local evidence.
Jakk
Black-box security scanner for MCP servers — deterministic single-call probes, no LLM. 13 probes across 7 surfaces.
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…
Scan Action
The first GitHub Action that scans MCP servers, AI agents & LLM pipelines for security vulnerabilities. 24 checks: tool poisoning, SSRF, prompt injection, DataFlow taint. Results…
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…
Synapsor Runner
Let AI agents query and update Postgres/MySQL without raw SQL, unrestricted schema access, or database credentials in the model; writes stay reviewed.
Bastyn Scan
Static analysis for AI and agent code: Python, TypeScript, JavaScript, MCP manifests, and dependency CVEs.
AI Tooling
MCP servers for red-team tooling (Mythic C2, BloodHound, nmap) plus LLM red-team reference: prompt injection / secret extraction and insecure output handling (XSS), each with a pr…
Safe MCP Agent
A local LLM agent (LangGraph + MCP) with a red-teamed guardrail layer and an automated evaluation harness that benchmarks security and task performance across models.
AI Agent Controlplane Demo
IBM Bob × ContextForge — a turnkey demo of the AI agent control plane: a governed MCP/A2A fintech mesh (OPA policy, PII/secret redaction, prompt-injection defense, RBAC least-priv…