Best Policy AI Skills & MCP Servers

Your personal AI runtime, local-first. Patchwork OS gives any AI model a consistent set of tools, YAML recipes, a delegation policy with approval queue, and a durable trace memory — all on your machine, all under your policy.

Official Prysmid MCP server — manage workspaces, apps OIDC, login policy, IdPs, branding, users from any MCP-compatible agent (Claude Code, Cursor, etc.)

MCP server that proxies all agent actions, classifies risk, enforces natural-language policies, and logs to a local SQLite audit DB with a live dashboard.

Cross-agent permission policy specification for AI coding agents

Cross-agent permission policy specification for AI coding agents

Cross-agent permission policy specification for AI coding agents

Cross-agent permission policy specification for AI coding agents

Cross-agent permission policy specification for AI coding agents

Cross-agent permission policy specification for AI coding agents

Agentic CVE remediation platform for Node.js. Correlates threat intelligence, applies policy-governed fixes, and delivers auditable remediation outcomes across CI/CD pipelines, agent workflows, and service portfolios.

Cross-agent permission policy specification for AI coding agents

Autonomous agent wallets with built-in spending policies for Ethereum

ASG Agent Pay — the banking layer for autonomous AI agents. Multi-chain payments (x402 + MPP), virtual cards, policy engine, and wallet abstraction across 17 networks. The only SDK unifying Coinbase x402 and Stripe MPP protocols.

MCP server for RiskState — pre-trade risk permissions for BTC/USD and ETH/USD. Spot, perps, and DeFi aware.

MCP security trust layer. Scan packages, inspect repo MCP dependencies, generate Policy Gate setup, check exposure, and query abuse data.

CuratedMCP's local-first action firewall for MCP servers

MCP server for Agence — AI governance framework with policy enforcement, skills, memory, and multi-LLM consensus

MCP server for cryptographic AI agent governance. Seal policy artifacts, enforce at runtime, prove with signed receipts and offline-verifiable evidence bundles.

hAIve MCP server — harness engineering tools for AI coding agents (briefing, enforcement, skills, memory lifecycle)

Axon SDK — typed TypeScript client for the local Axon trading daemon. Drive Hyperliquid perps, Uniswap V3 spot, Aave V3 lending, GMX v2 perps, wallets, and policy from AI agents or any Node.js script. Multi-chain: Arbitrum, Base, Avalanche, Polygon, Optim

MuHaven MCP server — read/position/policy toolsets bridging Claude Desktop / Cursor / Claude Code to the MuHaven backend, with a sibling muhaven-broker daemon holding the session-key private half over a local IPC socket

Model Context Protocol server for Open Policy Agent (OPA). Author, validate, debug, and explain Rego policies through any MCP-compatible client.

MergeGuide policy checking MCP server for Claude Code

Public Preview — AgentOS MCP Server for Claude Desktop: Build, deploy, and manage policy-compliant autonomous agents