AI agents call get_my_todos to retrieve information from A2AMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves agent TODO data without side effects. It is a simple query operation consistent with other read-only tools on the collaboration server. The incomplete description lowers confidence slightly, but the name and server purpose strongly indicate a Read operation. No destructive, financial, or code execution capability is present.
From the tool's definition Tool name 'get_my_todos' and context indicate data retrieval. Description 'Get agent' is sparse but the pattern of sibling tools (check_messages, get_recent_changes, list_active_agents, list_interfaces, query_agent, query_interface) all suggest read-only…
Documented attack patterns abuse exactly the kind of access get_my_todos 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 get_my_todos:
{
"version": "1",
"default": "deny",
"tools": {
"get_my_todos": {}
}
}get_my_todos 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 agent. It is categorised as a Read tool in the A2AMCP MCP Server, which means it retrieves data without modifying state.
Register the A2A MCP server in PolicyLayer and add a rule for get_my_todos: 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.
get_my_todos 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_my_todos 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_my_todos. 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_my_todos 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.