team-protocol
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@team-protocolWhat's the merge status for the verifier's handoff?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
GitMono Agent Team
面向 Libra + Monorepo 的最小三 Agent 协作仓库。它不负责替代模型或代码托管平台,而是把三个角色之间必须共享的工程契约固化为可验证文件和一个本地 MCP 服务:
Implementer(实现):在锁定的
baseCommit上完成受限范围的改动,交付 PatchSet 与自测证据。Verifier(验证):独立复跑验收、记录失败原因或通过证据,不能绕过测试结论。
Integrator(集成):检查基线、路径冲突、审查结论和风险门禁;只提交“允许合并”的决定,不直接替代人工审批。
架构遵循 GitMono 方案中的链路:IntentSpec → Task → PatchSet → Evidence → Decision。Libra 保存会话、checkpoint 与版本化证据;本仓库的 team-protocol MCP 只负责角色间的结构化交接和合并门禁。
快速开始
安装并初始化 Libra(或将现有 Git 仓库转换为 Libra 仓库)。
libra init --from-git-repository <your-repository> cd <your-repository> libra agent enable将 mcp/mcp.template.json 复制到所用 Agent 客户端的 MCP 配置,并把
<ABSOLUTE_PATH_TO_THIS_REPOSITORY>替换为本仓库绝对路径。libra是 Libra 官方示例中的 stdio MCP;team-protocol是本仓库提供的协作接口。复制 examples/intent-spec.example.json,为一次工作创建 IntentSpec。将同一文件、同一
baseCommit交给三个 Agent。按以下顺序交接:Implementer → Verifier → Integrator。每次交接由
team.submit_handoff写入.agent-team/handoffs.jsonl;集成前调用team.get_gate。npm test npm run demo
Related MCP server: Hivelore
目录
agents/ 三个角色的系统提示与边界
skills/ 三个角色可安装的 Agent Skill
contracts/ IntentSpec、Handoff 的 JSON Schema
mcp/ MCP 客户端配置模板与工具契约
src/mcp-server.js 无外部依赖的 stdio MCP 服务
src/protocol.js 校验、路由与合并门禁逻辑
examples/ 可复制的 IntentSpec / Handoff 样例
test/ 协议与 MCP 调用测试不可变协作规则
baseCommit是本轮协作的基线;任一 Agent 发现不一致必须阻塞交接。Implementer 只交付指定
allowedPaths内的 PatchSet 和其自测;Verifier 不修改同一 PatchSet。Verifier 的
passed交接必须包含通过的test证据;失败必须回传 Implementer。Integrator 的
approved决定必须建立在实现、通过测试和通过审查三类证据之上。risk: high永远需要human_approval证据,MCP 不会将其判为可合并。每次交接都应写入可选的 Libra
sessionId/checkpointId,使审计可追到 Think + Code 过程。
MCP 工具
工具 | 写入 | 用途 |
| 否 | 读取指定角色的输入、输出与允许交接方向。 |
| 是 | 验证并持久化一份角色交接记录。 |
| 否 | 按 Intent 查询已交接的证据链。 |
| 否 | 计算当前 Intent 是否达到合并门禁。 |
完整输入输出见 mcp/tools.md。JSON Schema 可用于 CI、Hook 或其他编排器;本服务不调用 LLM,也不直接执行 git merge。
与 Libra 的关系
Libra 是 Git 兼容、面向 Agent 的版本控制层,可捕获 Agent session 和 checkpoint,并原生提供 MCP 接入。这里按照其公开配置采用:
{
"command": "libra",
"args": ["code", "--stdio"]
}因此任务事实不在聊天窗口中漂移:IntentSpec 绑定 base commit,Handoff 绑定 PatchSet/Evidence,Libra trace 绑定会话与 checkpoint。详见 Libra README。
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityCmaintenanceProvides plan state management and phase gate enforcement for AI development loops. It tracks task progress and coordinates the lifecycle of agents by requiring specific evidence before advancing through development phases.10MIT
- Alicense-qualityBmaintenanceEnforces team knowledge and workflow policies for AI coding agents by providing context, decisions, and gates before code changes are made.1Apache 2.0
- AlicenseCqualityBmaintenanceEnables acceptance gates for AI coding-agent runs by recording evidence, running deterministic validation, applying a quality gate, and rendering auditable outcomes.7Apache 2.0
- Alicense-qualityAmaintenanceLocal-first AI agent for approval-gated automation and verifiable LLM workflows.1MIT
Related MCP Connectors
Durable agent-to-agent handoffs and shared scratchpad for multi-agent workflows.
Runtime AI governance: decision gates, human approval, hash-chained audit, compliance mapping.
Runtime permission, approval, and audit layer for AI agent tool execution.
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/marshawcoco/gitmono-agent-team'
If you have feedback or need assistance with the MCP directory API, please join our Discord server