AI agents call list_todos to retrieve information from Todo MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves existing todo data for the authenticated user. It performs no modifications, deletions, or external operations. The 'list' verb and description confirm it is a read-only operation, which is the lowest-risk category. Severity is low because unauthorized access would only expose the user's own todos, not system-wide impact or destructive capability.
From the tool's definition Tool name 'list_todos' and description 'List all todos for the authenticated user' indicate a retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access list_todos gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Todo MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for list_todos:
{
"version": "1",
"default": "deny",
"tools": {
"list_todos": {}
}
}list_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.
List all todos for the authenticated user. It is categorised as a Read tool in the Todo MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Todo MCP Server MCP server in PolicyLayer and add a rule for list_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 Todo MCP Server. Nothing to install.
list_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 list_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 list_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.
list_todos is provided by the Todo MCP Server MCP server (sholajegede/todo_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Todo MCP Server, 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.
11 Todo MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.