# A2p2a MCP server

Agent View of the PolicyLayer registry record for A2p2a: identity, probed posture, risk grade, and all 15 tools classified. HTML page: https://policylayer.com/tools/a2p2a

## Facts

- Server id: `tendQQ/a2p2a`
- Homepage: https://github.com/tendQQ/a2p2a
- Registry record: grade D, identity unverified
- Lifecycle: active
- Rate-limited: no
- Tools: 15
- Tool categories present: Execute, Read, Write
- Tags: a2p2a, automation
- Record last modified: 2026-09-27T11:39:12.395Z

## Tools (15)

| Tool | Category | Risk | Record |
| --- | --- | --- | --- |
| `manage` | Execute | High | https://policylayer.com/tools/a2p2a/manage.md |
| `run_flow` | Execute | High | https://policylayer.com/tools/a2p2a/run-flow.md |
| `agent_bus_state` | Read | Low | https://policylayer.com/tools/a2p2a/agent-bus-state.md |
| `analyze` | Read | Low | https://policylayer.com/tools/a2p2a/analyze.md |
| `intervene` | Read | Low | https://policylayer.com/tools/a2p2a/intervene.md |
| `list_agents` | Read | Low | https://policylayer.com/tools/a2p2a/list-agents.md |
| `list_flows` | Read | Low | https://policylayer.com/tools/a2p2a/list-flows.md |
| `list_workspaces` | Read | Low | https://policylayer.com/tools/a2p2a/list-workspaces.md |
| `read_group` | Read | Low | https://policylayer.com/tools/a2p2a/read-group.md |
| `read_scores` | Read | Low | https://policylayer.com/tools/a2p2a/read-scores.md |
| `report_progress` | Read | Low | https://policylayer.com/tools/a2p2a/report-progress.md |
| `say_in_group` | Read | Low | https://policylayer.com/tools/a2p2a/say-in-group.md |
| `talk_to_secretary` | Read | Low | https://policylayer.com/tools/a2p2a/talk-to-secretary.md |
| `post_goal` | Write | Medium | https://policylayer.com/tools/a2p2a/post-goal.md |
| `register_agent` | Write | Medium | https://policylayer.com/tools/a2p2a/register-agent.md |

## Tool descriptions

- `manage` — 让管理智能体（主代理）干一轮：看目标 → 按分数挑人 → 派活 → 群里说明。
- `run_flow` — 跑一条流程（flow 用 list_flows 里的文件名）。事件会自动投影进群，同时写 AgentBus。
- `agent_bus_state` — 读 AgentBus 里最近一条任务的状态与摘要（AI 之间沟通的内容，秘书就靠这个了解情况）。
- `analyze` — HR 打分：给每个智能体 + 流程打分（1–100），写快照，报告进群（有秘书则同时发秘书）。
- `intervene` — 对某个节点下发调整类干预（配色/风格/重做这一步）。改输出契约或流程结构会被拒绝。
- `list_agents` — 列出工作区里的智能体：角色、接入实例、线路模型、能力标签、擅长、分数、状态。
- `list_flows` — 可用流程文件名。
- `list_workspaces` — 列出所有工作区（= 工作群）及其开关（秘书 / AgentBus / HR）与打分节拍 N。
- `read_group` — 读工作群的近期消息（这是给人看的记录）。layer=human 只看人话，all 含机制类。
- `read_scores` — 读打分快照历史。
- `report_progress` — 读真实进展（AgentBus 摘要 + 调用记录），用来回答“现在什么进度”。
- `say_in_group` — 在主工作群发言。开了 AgentBus → 给管理智能体；没开 → 单 agent 直接干完。
- `talk_to_secretary` — 跟秘书说话：给目标 → 只把目标发到工作群（不出方案）；问进度 → 返回当前进展汇报。
- `post_goal` — 把「已经和主人聊清楚的目标」发到工作群，交给管理智能体定方案（秘书专用）。
- `register_agent` — 把自己（或别的智能体）登记进来：给一个名字 + 一条连接方式（命令行模板或 MCP 地址）。

## Related servers

- UnClick (1662 tools) — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server.md
- Apibase (1384 tools) — https://policylayer.com/tools/io-github-whiteknightonhorse-apibase.md
- Delx Mcp A2a (1068 tools) — https://policylayer.com/tools/io-github-davidmosiah-delx-mcp-a2a.md
- MCP Framework Personal (912 tools) — https://policylayer.com/tools/inggerman-mcps.md
- Hermoso (896 tools) — https://policylayer.com/tools/hermoso.md
- Nodebench (824 tools) — https://policylayer.com/tools/io-github-homenshum-nodebench.md
- Altium-MCP-Suite (817 tools) — https://policylayer.com/tools/altium-mcp-suite.md
- Eda Agent (777 tools) — https://policylayer.com/tools/eda-agent.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=a2p2a · API: https://policylayer.com/registry/api · Recommended policies for every tool: https://policylayer.com/policies/a2p2a