- Conduid
- Marketplace
- #zero-trust
MCP servers tagged zero-trust
182 live MCP servers tagged "zero-trust", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with zero-trust.
Reg AI Engine
Air-gapped, zero-egress AI execution & evaluation engine for audited enterprise environments. Async-first multi-tenant RAG, agentic DAG routing, and offline DeepEval CI/CD gates.
Code Protonbound
A secure Python MCP server for Proton Bridge with a deny-by-default security model, opt-in SMTP capability, and email body injection fencing.
Vcp
VCP — Verifiable Capability Protocol: zero-trust capability execution for AI agents. A stricter sibling of MCP where models plan and a signed gateway enforces. Signed content-addr…
Coreason Workspace Env
A headless, opinionated LangGraph DeepAgent platform for building, testing, and deploying zero-trust AI systems as native MCP servers.
Bounded Local AI Demo
OS-enforced isolation demo for bounded local AI: an agent reaches a private vault only through the severino-vault-mcp sensitivity gate, with no filesystem bypass.
Vault Server
Zero-trust key management MCP server — AES-256-GCM, Circuit Breaker, IAM labels, Cloud Armor WAF
Holmesgpt Tbot Demo
Teleport Machine & Workload Identity demo: an AI SRE (HolmesGPT) investigates Kubernetes with its own tbot identity — bound-keypair join, short-lived certs, RBAC-scoped, every cal…
AI Agent Security Control Plane
Defense-in-depth security control plane for autonomous AI agents using MCP, OPA/Rego, human approval, adaptive risk, detection, and automated containment.
Vaultsaas
Self-hosted MCP credential gate for AI agents — short-lived leases, human approval, one-command revoke, tamper-evident audit. Pure Apache-2.0, no SaaS.
Gemini Proxmox
Proxmox VE operations gateway exposing Model Context Protocol (MCP) Streamable HTTP to Google Gemini with built-in OAuth 2.0 / OIDC
Agentic Covenants
A practitioner framework for autonomous-agent governance: six matrices mapped to NIST CSF 2.0, with working Kyverno policies, Falco rules, and kill-switch runbooks in every popula…
Gateway Production Patterns
Production patterns for secure multi-tenant MCP gateways: Zero-Trust, federation, HITL, sandboxing
Trust Scoreboard
Open-source MCP security dashboard and trust scoreboard for Model Context Protocol servers, AI agents, tools, permissions, identity, provenance and risk.
P0 Security
P0 Security — independent third-party profile of a public API surface, by API Evangelist. P0 Security is a cloud-native Privileged Access Management (PAM) platform that governs ru…
Eczid Agent Trust
Official ECZ-ID Agent Trust product and documentation hub. Local-first agent inventory, authority and change inspection for VS Code.
Sovereign Mini Datacenter
Self-powered solar micro-datacenter stack for complete data & compute sovereignty. Features local AI inference, multi-agent copilots, space DTN (RFC 9171), post-quantum security,…
Autonomous Sovereignty Engine
Deterministic runtime engine and operational framework for high-agency builders: local zero-telemetry MCP mesh, 5-pillar sovereignty audits, OpSec sanitization, and cryptographic…
D8a
Blind MCP gateway: secure HTTP access to internal services without exposing data or credentials.
FLOWORK AGENT
Official Multi-OS Desktop Agent & Sovereign AI Canvas Host for Flowork OS. Clean partitioned distributions for Linux & Windows with Zero-Prompt-Bloat runtime.
Vantisso Releases
Binary releases of Vantisso — a control plane for running AI agents in isolated Firecracker MicroVMs. Source is not published here.
Krusch Fs MCP
Standalone OS filesystem & multi-node SSH fleet RAG MCP server. Indexes PDFs, docs, and system configs in-place—anchoring every agent memory and citation directly to a 1-based Kru…
Beamhall
Self-hosted MCP backplane for agent-built internal apps: AI coding agents ship apps that inherit compute, data, secrets and identity — no credentials, governed and audited.
Sevlex MCP Gateway
Layer 7 Zero-Trust Security Gateway & Control Plane for the Model Context Protocol (MCP).
Warden
A security proxy for the Model Context Protocol. Every tool call gets integrity-checked, policy-checked, inspected, and audited before it runs.
Keygate
面向 AI Agent 的零信任凭证网关 - 让 AI 安全访问 API，密码永不进入 LLM 上下文
Agentbond
Zero-trust capability delegation for MCP multi-agent systems. Solves the confused deputy problem with scoped JWT tokens, deterministic enforcement, and full audit trail.
Safe Skills
🛡️ Zero-trust security gate & vulnerability scanner for AI agent skills (Claude Code, Antigravity, OpenCode, Codex). Powered by NVIDIA SkillSpector.
Sentinel MCP
Capability-gated security reverse proxy and policy enforcer for the Model Context Protocol
Entra Identity Posture MCP
Read-only MCP server that audits Microsoft Entra ID app registrations and Conditional Access policies against Zero Trust principles, then generates dry-run remediation scripts for…
Enterprise MCP Server
enterprise-mcp-server
OmegaMobile
No description published.
SovereignMediaMobile
No description published.