workflow-guard-mcp
workflow-guard-mcp
为使用 Model Context Protocol (MCP) 的编码智能体客户端提供可移植的安全护栏。
该项目旨在通过向客户端提供一个共享的策略决策点,来缩小快速、高度自主的编码工作流的爆炸半径。MCP 服务器本身不执行拟议的操作。
状态
本仓库是一个早期脚手架。当前的 guard_check 工具展示了一种稳定的策略决策契约;它还不是 opencode-workflow-guard 策略的完整移植。
最重要的是,连接一个 MCP 服务器并不会使其成为编码客户端可执行的每个原生工具的拦截器。强制实施取决于宿主对集成的支持。参见 兼容性 和 计划。
Related MCP server: Vaikora Guard MCP
工具
guard_check:评估提议的shell、file_write、git或network操作,并返回allow、deny或ask以及一个机器可读的策略 ID。guard_status:报告服务器当前的执行模式。它明确地将此脚手架标识为依赖宿主的策略建议。
开发
需要 Node.js 20 或更高版本。
npm install
npm test
npm run typecheck
npm run build初始传输使用 stdio,因为 Claude Code 和 Codex 都支持本地 stdio MCP 服务器。可以在不更改策略 API 的情况下添加 Streamable HTTP。
设计原则
对外承诺的范围刻意窄于“此 MCP 会将你的编码智能体沙箱化”。它将策略集中化。客户端适配器在客户端暴露可信拦截机制的任何地方强制执行该策略;否则,结果仍仅为建议,并应与客户端原生的沙箱和审批控制结合使用。
来源
兼容性设计已于 2026-08-27 对照当前官方文档和源代码进行了核对:
Anthropic Claude Code MCP:https://docs.claude.com/en/docs/claude-code/mcp
Anthropic Claude Code hooks:https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/hook-development/SKILL.md
OpenAI Codex:https://github.com/openai/codex
Codex MCP 配置实现:https://github.com/openai/codex/blob/main/codex-rs/config/src/mcp_types.rs
MCP TypeScript SDK:https://github.com/modelcontextprotocol/typescript-sdk/blob/v1.29.0/docs/server.md
许可证
MIT
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Tools
Related MCP Servers
- AlicenseAqualityDmaintenanceRuntime policy enforcement for AI agents. Evaluate every agent action against your organization's policies before execution, with observe and enforce modes.11MIT

Vaikora Guard MCPofficial
AlicenseNot gradedqualityDmaintenanceEnforces deterministic policies on AI agent tool calls, evaluating actions against compliance modules (SOC 2, HIPAA, GDPR, etc.) and returning ALLOW, BLOCK, or CONSTRAIN decisions with an audit trail.MIT- FlicenseNot gradedqualityBmaintenanceEnables AI coding agents to evaluate actions against team-defined policies, record decisions, and obtain human approvals for potentially risky operations.1651
- FlicenseNot gradedqualityCmaintenanceEnables controlled AI-agent access to enterprise-shaped tools with a deny-by-default gated write path, human approval, dry-run execution, and append-only audit logging.
Related MCP Connectors
Git-native policy layer for AI agents: check_action verdicts against rules approved via PR.
Runtime permission, approval, and audit layer for AI agent tool execution.
Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ultus-net/workflow-guard-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server