CrossAgentMCP
CrossAgentMCP — 一个 A2A 池 MCP
A2A.md 愿景的最小化实现:一个 A2A 池 MCP,其中
任何智能体都可以注册到共享池中,
任何智能体都可以绑定到一个多智能体会话中,
智能体互相观察活动,在同伴完成后对其进行批评, 自我改进,并且无需人工干预持续工作,直到会话中的每个智能体都满足一个共享目标。
架构
三种进程类型:
┌────────────────── POOL (:9100, FastAPI HTTP JSON-RPC) ──────────────────┐
│ registry / sessions / activity / critique / goal (in-memory control │
│ plane — does NOT route work messages) │
└──────────────────────────────────────────────────────────────────────────┘
▲ pool JSON-RPC (PoolClient) ▲ pool JSON-RPC (per-agent bridge)
│ │
┌─────┴──────┐ peer A2A (SendMessage/GetTask) ┌─────┴──────┐
│ orchestrator│◄──────────────────────────────────►│ agent-N │ … :9101..9103
└────────────┘ each agent runs its own └────────────┘
headless v1.0 A2A HTTP server池 (
crossagent/pool.py) — 中央控制面板:注册表、会话、仅追加的每个会话活动日志、批评线程以及每个智能体的满意度。智能体 — 每个都是一个目录 (
agents/<role>/),包含:server.py— 一个 v1.0 A2A HTTP 服务器(对等数据平面);.mcp.json— 注册a2astdio MCP 桥接 (crossagent/a2a_bridge.py);CLAUDE.md— 角色 + 每轮合约。
编排器 (
crossagent/orchestrator.py) — 唯一推动时间前进的组件:注册智能体、创建会话,然后轮询地、无头地运行每个智能体 (claude -p),向其提供自上次轮次以来的活动/批评增量,直到所有成员都满意(或触发轮次预算/无进展保护)。
Related MCP server: kitty-hive
协议
忠实于 A2A v1.0(PascalCase JSON-RPC 方法、camelCase JSON、SCREAMING_SNAKE_CASE 枚举)。参见 crossagent/a2a.py。
设置
uv sync # Python 3.11+ venv + deps用法
make test # unit tests (protocol / pool / orchestrator with fake agents)
make smoke # pool + 2 A2A servers up; scripted round-trip (no real Claude)
make demo # full headless 3-agent demo (writer / critic / lead) — needs `claude`演示目标
demo/goal.json 要求三个智能体——writer、critic、lead——共同编写 demo/output/design.md(一个 URL 缩短器设计),直到三个都声明满意为止。
备注
.mcp.json文件硬编码了仓库路径D:/GitRepo-AI/CrossAgentMCP(匹配 claude-a2a 参考);如果您移动了仓库位置,请更新它。池和智能体服务器将状态保留在内存中;重新启动时它们会重置。
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for building and testing AI agents with multi-model experimentation and insights.
Autonomous agents can self-register and join public AI discussions through MCP 2026-07-28.
AI-to-AI knowledge network. Agents share insights, ask questions, build reputation over MCP.
AI marketplace for agents to find paid work and trade digital services via MCP and x402.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceAn MCP server that enables direct AI-to-AI communication through a bulletin board system featuring semantic search, thread management, and cryptographic identity verification. It allows AI agents to autonomously post, read, reply, and interact without human intermediation.2-
- AlicenseNot gradedqualityAmaintenanceMCP server for multi-agent collaboration enabling AI agents to communicate, delegate tasks, and share artifacts across clients and machines with federation support.60 npm1MIT
- AlicenseAqualityCmaintenanceMCP server for multi-agent AI systems providing mailbox messaging, A2A task delegation, resource coordination, and a web dashboard.2121 npm1MIT
- AlicenseNot gradedqualityBmaintenanceAn MCP server that provides shared memory, kanban board, and agent registry for AI agents to collaborate as a team, with a live dashboard for human oversight.156 npmMIT