// SCAN REPORT

A2p2a

15 tools. 4 can modify or destroy data without limits.

4 write tools that can modify data. Rate limits recommended.

Last updated: 27 Sept 2026

4 can modify or destroy data

11 read-only

15 tools total

Community server · catalogue entry checked 12/09/2026

How to control A2p2a ↓

TOOL MAP

What A2p2a exposes to your agents

Read (11) Write / Execute (4) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous A2p2a tools

Execute · High run_flow Executes a workflow with automatic side effects including projecting events into group and writing to AgentBus state. Execute · High manage Triggers autonomous agent orchestration cycle: selects agents, assigns tasks, posts in group. Write · Medium post_goal Posts a clarified goal to a work group, triggering agent assignment workflow. Write · High register_agent Creates new agent registrations with connection details; enables arbitrary agent injection into a shared workspace system.

4 of A2p2a's 15 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control A2p2a

PolicyLayer is an MCP gateway — it sits between your AI agents and A2p2a, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "post_goal": {
    "limits": [
      {
        "counter": "post_goal_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "agent_bus_state": {
    "limits": [
      {
        "counter": "agent_bus_state_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register A2p2a — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON A2P2A →

Instant setup, no code required.

FULL CATALOGUE

All 15 A2p2a tools

EXECUTE 2 tools

Execute 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。 Execute 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。

WRITE 2 tools

Write 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）。 Write 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）。

READ 11 tools

Read 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）。 Read 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）。 Read 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。 Read 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。 Read list_flows 可用流程文件名。 Read 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 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 read_scores 读打分快照历史。 Read report_progress 读真实进展（AgentBus 摘要 + 调用记录），用来回答“现在什么进度”。 Read 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。 Read 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。

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about A2p2a

How do I prevent bulk modifications through A2p2a? +

The A2p2a server has 2 write tools including post_goal, register_agent. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach A2p2a.

How many tools does the A2p2a MCP server expose? +

15 tools across 3 categories: Execute, Read, Write. 11 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on A2p2a? +

Register the A2p2a MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every A2p2a tool call.

Deterministic rules across all 15 A2p2a tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON A2P2A →

Instant setup, no code required.

15 A2p2a tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from A2p2a's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →