AI agents use query_agent to create or update resources in A2AMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your A2AMCP environment.
Sending a query to another agent is a Write operation: it creates a new message or communication object and delivers it to another party. While named 'query', the action is dispatching a message to an external agent, which constitutes a write/create side effect. It does not execute code or irreversibly destroy data, but it does produce a side effect by transmitting data to another agent.
From the tool's definition "Send query to another agent" — creates/sends a message or communication to another agent
Documented attack patterns abuse exactly the kind of access query_agent gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and A2AMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for query_agent:
{
"version": "1",
"default": "deny",
"tools": {
"query_agent": {
"limits": [
{
"counter": "query_agent_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}query_agent stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Send query to another agent. It is categorised as a Write tool in the A2AMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the A2A MCP server in PolicyLayer and add a rule for query_agent: 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 A2AMCP. Nothing to install.
query_agent is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the query_agent 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.
Set action: deny in the PolicyLayer policy for query_agent. 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.
query_agent is provided by the A2A MCP server (webdevtodayjason/a2amcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from A2AMCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
17 A2AMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.