- 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.
Lucinlabs
Static analysis for AI agent tools. Reads the function body, not the tool description.
Autonomyproof CLI
Prove what authority your AI agent holds — and fail the PR that grants new unsafe authority. Open-source, local, deterministic.
LLM Security Payloads
A defender's field guide to attacks on LLM apps — prompt injection, jailbreaks, system-prompt extraction, data exfiltration — mapped to OWASP LLM Top 10, each with its defense. EN…
Trifecta
Find and block the lethal trifecta that forms across your MCP servers.
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.
Openclaw Install Tools
Simplify OpenClaw setup with guided install steps, LAN file transfer, and AI-powered error diagnosis for macOS and Windows users.
Bouclier AI
Open-source, certificate-free prompt-injection monitor and optional blocker for macOS AI coding agents — on-device detection; no accounts or passive app telemetry.
Malwar
Static analysis engine for detecting malware in agentic AI skill files
AI Security Roadmap
Bilingual, evidence-led roadmap for LLM, RAG, agent, MCP, red-team, and blue-team security.
Silmaril
Silmaril — independent third-party profile of a public API surface, by API Evangelist. Silmaril is a Y Combinator-backed runtime security company that builds an AI application fir…
Access AI Gateway
LLM gateway over a multi-tenant access-control system, with guardrails against indirect prompt injection and cross-tenant data exposure.
Redcell
Security layer for AI agents — score the system prompt, firewall untrusted input, screen every tool call. Deterministic, 0-API, runs at the edge.
Awesome Agent Security
A curated list for securing autonomous AI agents — configs, runtime, tools, MCP, and red-teaming
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.
Agent Threat Scanner
面向 AI 智能体生态的安全扫描器，支持检测 Skills、MCP 服务、智能体配置及工具集成中的安全威胁。/ Privacy-first security scanner for AI agent artifacts, including Skills, MCP servers, agent configurations, and tool integr…
Mcphound
Independent security scanner and reputation layer for MCP servers and agent skills
Xclaude Gateway
Durable local audit trail for Claude Code and MCP tool activity. Records, classifies and keeps the history on your Mac.
Purplegate
purplegate — Red/blue-team CI gate for agentic-AI apps. Prompt-injection, secrets, SAST, deps, IaC/RLS, workflow injection, MCP checks. One signed GitHub Action, mapped to OWASP L…
Interceptor Bench
Empirical comparison of MCP interceptor placements for prompt-injection defense.
Promptwall
A firewall for LLM traffic: detect prompt injection, jailbreaks, and secret/PII leaks. Zero-dependency Python library + CLI + MCP server.
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
Promptsonar
Static security scanner for AI prompts, MCP configs, and agent workflows. Zero LLM calls. Local-first. OWASP LLM Top 10 aligned.
Ctxguard
Scan a repository for prompt-injection payloads before you point an AI coding agent at it.
Agentlock
An MCP server wrapper that gates tool calls on where a value came from, not what it says. Catches cross-hop prompt-injection laundering.
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.
Agentx MCP
Keyless MCP security shield: wrap any MCP server so a poisoned tool call cannot wreck your system and your agent keeps working. Launcher for agentx-security-sdk.
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
Detonator
Dynamic exploitability testing for AI agents and the MCP servers they use
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.
Policy Gateway
Runtime policy enforcement and adversarial evaluation for MCP tool calls
Aibom
Generate an AI bill of materials for models, MCP servers, tools, datasets, vector stores, and external APIs.
Neon Guard MCP
Local-first MCP security proxy for Neon Postgres: gives AI agents scoped branch/test access while air-gapping your master key and production data.
Strike
Active adversarial security scanner for Model Context Protocol (MCP) servers: runtime attacks, LLM-as-judge, and an adaptive agent.
Mcpsnare
Active security scanner that pentests MCP (Model Context Protocol) servers. Triggers and out-of-band-confirms real vulns (RCE, SSRF, path traversal, auth bypass) with graded confi…
Gateward
Security gateway for MCP traffic. 5 built-in rules block prompt injection, credential leakage, path traversal, cross-repo exfiltration, and destructive commands. One pip install,…
Bansho
An MCP security gateway. Adds auth, rate limits, and audit logging between your AI client and any MCP server.
Mcpsafe
The first MCP security framework that tests a live running server, not just static config. Runtime adversarial testing — prompt injection, fuzzing, load & concurrency, latency, au…
Agent Security Lab
A local, dependency-free lab that reproduces MCP / AI agent attacks and the audit that catches them. Educational and defensive. Runs on python3 alone, offline.
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…
Sentrymcp
A static + runtime security scanner for MCP (Model Context Protocol) servers
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…
Heron MCP
Free, signed 0-100 trust scores for what an AI agent runs: skills, MCP servers, and the agent itself. Public methodology, wallet-signed (EIP-191).
Security Platform
Mediate, don't classify: runtime security gateway for MCP tool calls - identity, OPA policy, credential brokering, signed provenance, audit. Reference implementation.
Prompt Injection In LLMs
Implemented and evaluated protection mechanisms to determine their effectiveness against direct prompt injection attacks.
AI Protect
AI-application security assurance pipeline: tier-aware SAST · DAST · AI red-team scanning with a findings dashboard, CVE intel feeds & auto-remediation. For AppSec & platform team…
Prompt Injection Lab
Hands-on prompt injection lab with live attack demos for agent, MCP, and memory poisoning training.
Agent Guard Lite
Runtime security guard for LLM agents and MCP: prompt-injection detection, tool policy enforcement, and SQLite traceability.
Tool Poisoning Toolkit
Demonstrates MCP tool poisoning (malicious tool descriptions/schemas) with a runnable vulnerable server + a detection scanner. Includes real captured example output.