MCP servers and skills: search, filter by where they run, and compare.
Reference implementation of chain-aware authorization for agent-to-agent (A2A) traffic, using Open Policy Agent.
GoMIT★ 1Few starsNo key
OPA-backed policy_engine plugin (dev.mcpg.policy.opa, v0.2 remote + embedded WASM)
MCPLink onlyFew stars
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
🧠 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
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
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
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
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
Composable tool mesh for MCP ecosystems — server registry, capability normalization, trust policies, capability routing, and audit for agentic tool platforms.
PythonMIT★ 2Few starsNo key
A plug-and-play security gateway for Model Context Protocol (MCP) servers. Adds JWT/OIDC authentication, RBAC, SQL firewall, OPA policy enforcement, taint tracking, DLP filtering, and a tamper-evident
SkillMIT★ 1Few starsNo key
A runnable reference architecture for governed enterprise AI - every AI action policy-checked by OPA, audited, and traceable to a source document. 18 containers, one 'make demo'. MCP-native, ISO 27001
SkillApache-2.0Few starsNo key
A high-performance security gateway for the Model Context Protocol.
GoMIT★ 3Few starsNo key
Inline policy enforcement proxy for AI agents: OPA policies on MCP tool calls, human approval for risky actions, and a hash-chained audit ledger.
SkillApache-2.0★ 1Few starsNo key
Live enterprise agent systems lab: LangGraph, MCP, OPA, AI SDK, real tools, and agentic-vs-rules execution.
SkillMITFew starsNo key
Reference implementation of ZT-MCP: a zero-trust security architecture for MCP-connected AI agents. Includes TIV, APE, DCOF, PAL enforcement components with formal CapBAC access control model.
SkillMITFew starsNo key
Agent Trust Passports and Action Levels: who an agent acts for, what it may do alone, and when that ends. Schemas and a validator.
PythonApache-2.0Few starsNo key
The open-source, extensible LLM gateway and agentic MCP proxy. Build, audit, and route prompts to 100+ LLMs with unified telemetry and access controls
SkillApache-2.0★ 1Few starsNo key
OpenTelemetry MCP Server — expose traces, metrics, logs, and ZK proofs to AI agents via the Model Context Protocol
Node.jsApache-2.0Few starsNo key
Policy gateway for MCP: authenticate each agent, enforce least-privilege tools, mask and strip responses, and write a tamper-evident audit log.
PythonApache-2.0Few starsNo key
Production-grade security, observability, and governance for Model Context Protocol (MCP) servers. Make any MCP server enterprise-ready in minutes.
SkillMIT★ 2Few starsNo key
Governed multi-agent security response on GKE: Vertex AI Gemini triage, OPA policy decisions, Cloud KMS-signed human approvals, and remediation through an mTLS MCP gateway. Built with Terraform and Pu
MCPLink onlyFew stars
Who stands behind it
