Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
Model Context Protocol server for Open Policy Agent (OPA). Author, validate, debug, and explain Rego policies through any MCP-compatible client.
Node.jsMIT★ 8No key
MCP server giving LLM agents real authorization answers: evaluate Rego in-process via OPA, or ask an OpenID AuthZEN 1.0 PDP
DockerMIT★ 1Few starsNo key
Reference implementation of chain-aware authorization for agent-to-agent (A2A) traffic, using Open Policy Agent.
GoMIT★ 1Few starsNo key
Governance control plane for AI agents — policy enforcement at the tool-call, spawn, delegate, plan, and budget layer. OPA-backed, Apache-2.0.
PythonApache-2.0★ 4Few starsNo key
Minimal, reproducible demonstration for the work "Agentic FIWARE: MCP and Guardrail Generic Enablers for Secure and Auditable Smart City Orchestration". It wires together an MCP server (FastAPI), FIWA
PythonMIT★ 4Few starsNo key
Duke Agent Fabric 是一个面向企业与政务场景、支持私有化部署的生产级多智能体运行平台。基于 LangChain 与 LangGraph 构建,可实现内部知识检索、公文生成与审校、会议纪要、文件比对、敏感信息扫描及 MCP 工具自动 化;内置 Redis/MySQL 分层记忆、租户/用户/Agent/会话上下文隔离、Keycloak OIDC 身份认证、OPA 策略与密级校验、敏感内
PythonApache-2.0★ 1Few starsNo key
Exploring MCP security: prompt injections, leaks, auth bypasses, OPA policies, and quirky edge cases. A playground for safe, educational, and cutting-edge model security experiments.
SkillApache-2.0Few starsNo key
Runtime security platform for LLM agent tool calls on Kubernetes
PythonApache-2.0★ 26No key
🧠 Open-source context engine that feeds AI agents with policy-compliant enterprise knowledge. MCP-native, GDPR & EU AI Act ready, self-hosted.
SkillApache-2.0★ 5No key
Inline MCP governance proxy — OPA/Rego policy enforcement, DLP scanning and prompt-injection detection on every tool call, before it executes.
PythonApache-2.0★ 1Few starsNo key
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-privilege), provable with
SkillMIT★ 1Few starsNo key
Open source MCP Gateway written in Go. Stateless core, OPA authorization, OpenTelemetry observability, and a plugin system for extending tools. Designed for self-hosted HA deployments on Kubernetes.
SkillApache-2.0Few starsNo key
System of record for AI tool risk: inventory, policy enforcement, approvals, and audit-ready evidence.
SkillApache-2.0★ 3Few starsNo key
Runtime governance and tamper-evident audit evidence for AI agent MCP tool calls
PythonApache-2.0★ 1Few starsNo key
Runtime security & governance control plane for AI agents. Enforces per-tool authorization, OPA policy, behavioral risk scoring, blast-radius analysis, autonomy contracts, and tenant kill-switch. Ever
PythonApache-2.0★ 5No key
RLM (persistent Python + persistent sub-agents + continual harness) for the coding agent you already use — Claude Code, Codex, opencode
SkillApache-2.0★ 1Few starsNo key
Zero-trust gateway for AI systems. OPA policies, audit logging, authentication (OIDC/LDAP/SAML), MCP/HTTP/gRPC adapters. FastAPI + Rust extensions. Production-ready.
SkillMIT★ 1Few starsNo key
Mediate, don't classify: runtime security gateway for MCP tool calls - identity, OPA policy, credential brokering, signed provenance, audit. Reference implementation.
SkillMITFew starsNo key
Read-only MCP server for Trino: six tools, writes refused on the SQL tree, one configured Trino identity, bounded rows and time. Any MCP host, any model.
PythonApache-2.0★ 4Few starsNo key
Composable tool mesh for MCP ecosystems — server registry, capability normalization, trust policies, capability routing, and audit for agentic tool platforms.
PythonMIT★ 2Few starsNo key
MCP server giving AI coding agents (Claude Code, Cursor, Codex) a queryable source of engineering constraints — policy-as-code guardrails for AI-generated code, backed by OPA, Conftest, Checkov & Semg
PythonApache-2.0Few starsNo key
Reference implementation of the MCP authorization spec (2025-11-25) for enterprise deployments: an OAuth 2.1 gateway that brokers Microsoft Entra ID, enforces three-layer OPA policy, never passes clie
SkillMITFew starsNo key
Control plane for safely exposing LLM providers to your teams
GoMIT★ 1Few starsNo key
Who stands behind it