a2a_cancel_task

THE RISK

Critical Risk

An AI agent that decides to call a2a_cancel_task doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from A2A Client MCP Server is gone — there is no undo for destructive operations.

Documented attack patterns abuse exactly the kind of access a2a_cancel_task gives an agent:

HOW TO CONTROL A2A_CANCEL_TASK

PolicyLayer is an MCP gateway — it sits between your AI agents and A2A Client MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for a2a_cancel_task:

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "a2a_cancel_task"
  ]
}

a2a_cancel_task disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

Create a free account and register A2A Client MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RESTRICT THIS TOOL →

Free to start. No card required.

EXPLORE

More A2A Client MCP Server tools

Write a2a_send_task Send a task to an A2A agent Write a2a_send_task_subscribe Send a task and subscribe to updates (streaming) Read a2a_agent_info Get information about the connected A2A agents Read a2a_get_task Get the current state of a task

All 5 A2A Client MCP Server tools →

Destructive tools on other servers

Frida Game Hacking MCP clear_scan MegaMemory remove_concept Frida Agent MCP kill_app 1MCP Server mcp_uninstall

Go deeper

Critical-risk tools in A2A Client MCP Server → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

What does the a2a_cancel_task tool do? +

Cancel a running task. It is categorised as a Destructive tool in the A2A Client MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on a2a_cancel_task? +

Register the A2A Client MCP Server MCP server in PolicyLayer and add a rule for a2a_cancel_task: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches A2A Client MCP Server. Nothing to install.

What risk level is a2a_cancel_task? +

a2a_cancel_task is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit a2a_cancel_task? +

Yes. Add a rate_limit block to the a2a_cancel_task rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block a2a_cancel_task completely? +

Set action: deny in the PolicyLayer policy for a2a_cancel_task. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides a2a_cancel_task? +

a2a_cancel_task is provided by the A2A Client MCP Server MCP server (tesla0225/mcp-a2a). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every A2A Client MCP Server tool call.

Deterministic rules across all 5 A2A Client MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

GOVERN A2A CLIENT →

Free to start. No card required.

5 A2A Client MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// WHAT A2A_CANCEL_TASK ON A2A CLIENT MCP SERVER DOES

// THE RISK

// HOW TO CONTROL A2A_CANCEL_TASK

// EXPLORE