- Conduid
- Marketplace
- #agent-security
MCP servers tagged agent-security
47 live MCP servers tagged "agent-security", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with agent-security.
Nono
Sandbox any AI agent in seconds - zero setup, zero latency.
Template Repo
Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability on sleeper agents, and agent integration via CLI wrappers
Medusa
AI-first security scanner with 76 analyzers, 4,000+ detection rules, 508 FP filters (96.8% reduction), and 133 CVE detections for AI/ML, LLM agents, and MCP servers
Gateway
A plugin-based gateway that orchestrates other MCPs and allows developers to build upon it enterprise-grade agents.
Cupcake
A native policy enforcement layer for AI coding agents. Built on OPA/Rego.
Agent Security Scanner MCP
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis,…
Compliant LLM
Build Secure and Compliant AI agents and MCP Servers. YC W23
agentos-server
[DEPRECATED] Moved to microsoft/agent-governance-toolkit
Honeymcp
Open-source honeypot for MCP (Model Context Protocol) servers. Collects threat intel on attacks against the AI agent ecosystem.
Agentic Security
Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪
Mcptrust
Runtime security proxy for MCP: lockfile enforcement, drift detection, artifact pinning, Sigstore/Ed25519 signing, CEL policy, OpenTelemetry tracing. Works with Claude Desktop, La…
Arcjet Js
Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your JS/TS…
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…
Reins
Runtime security for OpenClaw agents. Scan, fix, monitor.
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.
Penetration Testing
The ultimate OWASP MCP Top 10 security checklist and pentesting framework for Model Context Protocol (MCP), AI agents, and LLM-powered systems.
nickpending/mcp-recon
Reverse-engineer MCP server tool surfaces. Enumerate, fuzz, classify, report. CLI + library.
Helm AI Kernel
Fail-closed execution firewall for AI agents: quarantine MCP tools, proxy OpenAI-compatible requests, emit signed receipts, and verify EvidencePacks offline.
Clawseccheck
🦞 Local, read-only security scanner for OpenClaw. Finds config, prompt-injection and supply-chain risks — A–F grade.
Multi Agent Workflow Lab
Testing and observability for multi-agent delegation, MCP tools, permissions, sandboxed actions, prompts, and workflow replay.
Opena2a CLI
Unified CLI for the OpenA2A security platform
Aegis Memory
Secure context engineering for AI agents. Content security · integrity verification · trust hierarchy · ACE patterns. Self-hosted, Apache 2.0.
Agent Mesh
[DEPRECATED] Moved to microsoft/agent-governance-toolkit
Signet
Cryptographic action receipts for AI agents — sign, audit, verify.
Bluerock
Runtime visibility for Python MCP servers. Captures tool calls, session lifecycle, module imports (SHA-256), and subprocess execution as structured NDJSON. No code changes. Apache…
Dcp
Permission layer for AI agents — wallet signing, vault access, budgets, and human approvals.
Authsome
Local credential vault for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see your credentials.
Trustabl
Static analyzer for agent reliability.
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.
Ryk
Guardrails for coding agents. Run Pi, Hermes, OpenCode, Codex, or Claude through ryk with policy, approvals, 86 safety packs, and a local audit trail.
Agentaudit
Security scanner for AI agent packages — CLI + MCP server
Install Guard
Scan MCP servers before installing them
Risk
Audit MCP configs and servers for risky tools, secret exposure, and prompt-injection patterns.
Nominee
Decision-bound Model Context Protocol tool handlers for governed AI agents
Tool Gateway
Local-first governed tool execution gateway for AI agents. Read/write classification, policy evaluation, signed execution receipts, multi-key rotation with cross-signed chain snap…
Golf Scanner
Discover and audit MCP servers for security vulnerabilities across Claude Code, Cursor, VS Code, and more
Mcps Ha
High Availability extension for MCPS – signed state sync, nonce replication, rogue server detection. Install on top of mcp-secure.
Sint Protocol
Open protocol and reference stack for governing AI agent actions in physical and safety-critical systems
sint-ai/sint-protocol
risk audits.
Mythos Sentinel
Agent permission firewall for MCP tools, shell, files, and x402/Base payments.
Patient Zero
Supply-chain attack scanner for the agent era. Triage in 30s with `npx patient-zero`, block malicious installs before postinstall runs, or drop into CI as a GitHub Action. Covers…
Firmis Scanner
AI agent runtime security scanner - detect malicious behavior in Claude Skills, MCP Servers, Codex Plugins, and more
askalf/truecopy
mcp proxy exposes only pinned, unmodified tools from a live server.