AI agents use add_todo 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.
Adding a todo item creates new data in the Redis-backed coordination system but is reversible (todos can be deleted or modified). This is a Write action with minimal blast radius since it only affects the agent's own task list and cannot cause irreversible damage or trigger external operations. Severity is low because the impact is confined to coordination metadata rather than shared codebase or external systems.
From the tool's definition Tool name 'add_todo' and description 'Add a todo item' indicate creation of a new data entry. The verb 'add' combined with the todolist context shows this is a write operation that creates reversible data.
Documented attack patterns abuse exactly the kind of access add_todo 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 add_todo:
{
"version": "1",
"default": "deny",
"tools": {
"add_todo": {
"limits": [
{
"counter": "add_todo_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_todo 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.
Add a todo item. 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 add_todo: 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.
add_todo 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 add_todo 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 add_todo. 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.
add_todo 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.