AI agents call get_task_result to retrieve information from MCP-A2A-Gateway without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve or query task result data based on its name, fitting the Read category (retrieves data with no side effects). Severity is medium because the tool could expose task results that might contain sensitive information depending on what tasks are being run in the A2A agent ecosystem, but there is no evidence of destructive or financial impact.
From the tool's definition Tool name 'get_task_result' indicates retrieval of task results without modification. No description provided to clarify scope.
Documented attack patterns abuse exactly the kind of access get_task_result gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-A2A-Gateway, and nothing reaches the server without passing your rules. This is the rule we recommend for get_task_result:
{
"version": "1",
"default": "deny",
"tools": {
"get_task_result": {}
}
}get_task_result is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
get_task_result. It is categorised as a Read tool in the MCP-A2A-Gateway MCP Server, which means it retrieves data without modifying state.
Register the MCP-A2A-Gateway MCP server in PolicyLayer and add a rule for get_task_result: 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 MCP-A2A-Gateway. Nothing to install.
get_task_result is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_task_result 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 get_task_result. 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.
get_task_result is provided by the MCP-A2A-Gateway MCP server (yw0nam/mcp_a2a_gateway). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP-A2A-Gateway, 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.
6 MCP-A2A-Gateway tools catalogued and risk-classified — across an index of 43,000+ MCP servers.