mcp-guard

by permission-protocol · MCP 服务器 · ★ 10

About mcp-guard

MCP Guard Stop your AI agents from doing dangerous things. MCP (Model Context Protocol) is how AI agents call tools — like APIs, databases, or deployments. MCP has no built-in access control. MCP Guard adds that layer. Define what's allowed, blocked, or requires approval — in a single YAML file. MCP Guard sits between your MCP client and server, enforces the rules, and logs every decision as an audit receipt. Without MCP Guard, your agent can call any tool. With it, every action is checked. MCP Guard does not just log — it blocks execution before it happens.

agent-guardrailsai-agentsai-governanceai-safetymcpmodel-context-protocolruntime-governance

Quick Facts

Stars10
Forks6
LanguageTypeScript
CategoryMCP 服务器
Quality Score61.964/100
Open Issues1
Last Updated2026-06-15
Created2026-03-20
Platformsmcp, node
Est. Tokens~15k

More MCP 服务器 Tools

Explore other popular mcp 服务器 tools:

View all MCP 服务器 tools →

Popular TypeScript Agent Tools

  • openclaw ⭐ 379.1k · Codex 技能
  • n8n ⭐ 192.9k · MCP 服务器
  • dify ⭐ 145.6k · MCP 服务器
  • gstack ⭐ 110.8k · AI 工具
  • gemini-cli ⭐ 105.3k · MCP 服务器

Frequently Asked Questions

What is mcp-guard?

mcp-guard is MCP middleware that blocks dangerous AI agent actions using a simple YAML config. It is categorized as a MCP 服务器 with 10 GitHub stars.

What programming language is mcp-guard written in?

mcp-guard is primarily written in TypeScript. It covers topics such as agent-guardrails, ai-agents, ai-governance.

How do I install or use mcp-guard?

You can find installation instructions and usage details in the mcp-guard GitHub repository at github.com/permission-protocol/mcp-guard. The project has 10 stars and 6 forks, indicating an active community.

View on GitHub → Browse MCP 服务器 tools