// SCAN REPORT

A2AMCP

17 tools. 11 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 11 Jun 2026

11 can modify or destroy data

6 read-only

17 tools total

Community server · catalogue entry verified 11/06/2026

How to control A2AMCP ↓

TOOL MAP

What A2AMCP exposes to your agents

Read (6) Write / Execute (10) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous A2AMCP tools

Destructive · High unregister_agent Unregistering an agent and cleaning up its data is a destructive operation: the agent's identity, session state, and coordination metadata are permanently removed from the Redis-backed system. Write · Low add_todo Adding a todo item creates new data in the Redis-backed coordination system but is reversible (todos can be deleted or modified). Write · Low heartbeat The heartbeat tool writes status/presence data to the shared Redis store, enabling the coordination system to track which agents are active. Write · Low mark_task_completed The tool modifies existing data (marks a task as completed) in a Redis-backed coordination system.

11 of A2AMCP's 17 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control A2AMCP

PolicyLayer is an MCP gateway — it sits between your AI agents and A2AMCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "unregister_agent": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "announce_file_change": {
    "limits": [
      {
        "counter": "announce_file_change_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "check_messages": {
    "limits": [
      {
        "counter": "check_messages_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 A2AMCP — 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 A2AMCP →

Free to start. No card required.

FULL CATALOGUE

All 17 A2AMCP tools

DESTRUCTIVE 1 tools

Destructive unregister_agent Unregister agent and clean up

WRITE 10 tools

Write announce_file_change Lock a file before editing Write query_agent Send query to another agent Write respond_to_query Respond to a specific query Write add_todo Add a todo item Write heartbeat Send periodic heartbeat Write mark_task_completed Mark a task as completed Write register_agent Register an agent for a specific project Write register_interface Share a type/interface definition Write release_file_lock Release file lock after editing Write update_todo Update todo status

READ 6 tools

Read check_messages Check and retrieve messages Read get_my_todos Get agent Read get_recent_changes Get recent file changes Read list_active_agents List all active agents in a project Read list_interfaces List all shared interfaces Read query_interface Get shared interface definition

FAQ

Questions about A2AMCP

Can an AI agent delete data through the A2A MCP server? +

Yes. The A2AMCP server exposes 1 destructive tools including unregister_agent. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through A2AMCP? +

The A2AMCP server has 10 write tools including announce_file_change, query_agent, respond_to_query. 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 A2AMCP.

How many tools does the A2A MCP server expose? +

17 tools across 2 categories: Read, Write. 6 are read-only. 11 can modify, create, or delete data.

How do I enforce a policy on A2AMCP? +

Register the A2A 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 A2AMCP tool call.

Deterministic rules across all 17 A2AMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON A2AMCP →

Free to start. No card required.

17 A2AMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.