- Conduid
- Marketplace
- #policy
MCP servers tagged policy
45 live MCP servers tagged "policy", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with policy.
Ironcurtain
A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)
Congress
An MCP server allowing AI agents and MCP clients to interface with the Congress.gov API
Room
Standalone guardrail control plane and MCP sidecar for coding agents
Toolfence
Local, fail-closed policy enforcement and human approval for MCP tool calls.
Askgrokwallet
Rules-and-receipts layer for AI agents that spend money: plain-English policy → human approval → signed receipts anyone can verify.
Meho
Governance backplane for AI agents acting on infrastructure — policy-gated, audit-grade, MCP-native. Apache 2.0.
China Central Policy MCP
面向 gov.cn 的国务院政策检索与解析 MCP 服务器，提供“政策列表检索 + 政策正文抓取”两类工具，直接返回结构化数据。
Gutenberg CLI
From any API surface to verified AI agent tools: Go CLI + MCP + skills + SQLite + policy + proofs.
Tools Factory
From any API surface to verified AI agent tools: Go CLI + MCP + skills + SQLite + policy + proofs.
AegisTrace
AegisTrace - verifiable execution for durable AI agents. Compile policy-bound workflows, record every effect, replay without the network, and prove individual events.
Legislation
CLI tool for searching and retrieving New Zealand legislation data
Lynx
Policy-gated, durable, audited execution for AI agent tool calls. Every action gets a five-verdict policy check, a crash-safe checkpoint, and a tamper-evident audit event — a libr…
Claude Sec
Claude Code Enterprise Security Framework - Security approval and architecture for deploying Claude Code in enterprise environments
Rh
Client-side tooling for a Robinhood Trading MCP connection: enumerate and diff the live tool surface, and enforce policy guardrails on agent-initiated writes before they leave you…
Occ MCP Proxy
Policy enforcement for AI tool calls. Default-deny control for any MCP server.
Openclaw MCP Tool Policy
Per-MCP-server allow/deny policy for OpenClaw tool calls
Runtime Guard
Policy-based MCP tool call proxy
Aethis
MCP server for the Aethis developer API — eligibility checks via Claude, Cursor, Windsurf
Nominee
Decision-bound Model Context Protocol tool handlers for governed AI agents
Border Patrol
A policy-enforcing MCP gateway: one MCP server that proxies all your others and blocks dangerous tool calls
Policy Interceptor
A lightweight governance and policy interception layer for MCP servers.
Atbash
Atbash safety judge exposed as a standalone MCP server
ToolMux
Connect terminal workflows and local agents to SaaS tools and remote MCP servers with local credentials and policy checks.
Runwitness
Autonomous agents with receipts.
Provio
A safety floor your AI agents can't get under: one policy for Claude Code, Codex, Gemini CLI, Cursor, Windsurf and MCP, judged by what each call will run, backstopped by the kerne…
Homebound
Zero-trust control layer for AI-powered homes
Moat
Verified Agent Capabilities Marketplace — MCP-first trust + policy + execution layer for agents
Stream Types
Streaming governance types for AI agents. The agent proposes. The policy engine disposes.
Agent Authz
Secure-by-default authorization PEP for APIs, Agent tools, RAG, and tasks
sidclawhq/mcp-guard
no SDK needed.
Zero Trust Layer
Open-source, self-hosted Zero Trust policy enforcement layer for MCP servers.
Congressmcp Bridge
A bridge package allowing Claude Desktop or any stdio MCP client to connect to remote congressMCP
PolicyNIM
PolicyNIM is a policy-aware engineering preflight layer for AI coding agents.
Policy Forge
Least-privilege MCP tool policy generator, validator, risk scorer, diff reporter, and CI gate.
Policy Enforcement
MCP server for Claude Code: Policy compliance and system health checks.
Toolgraph
Graph-native MCP tool registry: explainable, advisory governance and impact analysis over a tool/policy graph
OpenARD
Neutral self-hosted registry and toolkit for Agentic Resource Discovery.
Tool Call Guard
Deny-by-default policy gate for AI agent tool calls — allowlists, validation, rate caps, approval hooks, audit trail. One policy model, enforced in JavaScript and Python.
Workspace Metabolism
Govern what Claude Code, Codex, Aider and OpenClaw leave in your workspace: one JSON policy file, audit, recyclable clean, rollback, hash-chained audit trail.
PolicyAgents
基于 LangGraph + LangChain + MCP 的政策文本深度分析工具，提供极致的用户交互体验。
Agent Guard 1.0.0
🚀 ApexGuard: Zero-Trust Enforcement Layer for Multi-Agent LLM Systems
Atlas Shield Spec
Open specification & example policy packs for Atlas Shield to protect AI agents from prompt injection & data exfiltration (MCP-compatible).
Permission Policy Tester
Scan MCP tool descriptions and schemas for risky permission policy signals.
OpenAgentsGate
One policy, audit, replay, and revocation layer for Codex, Claude Code, MCP tools, CI agents, and custom agent scripts.
LLM Tool Bridge
Validated model-to-tool dispatch with typed payloads.