获取所有到期且未完成的待办事项
AI agents call get_pending_todos to retrieve information from MCP Reminder without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and lists existing todo items without creating, modifying, deleting, or executing any actions. It is purely informational, making it a Read operation with low severity since exposure poses minimal risk—at worst, an AI agent reads task information without consequence.
From the tool's definition Tool name 'get_pending_todos' and description indicating retrieval of pending todos—'获取所有到期且未完成的待办事项' translates to 'get all expired and uncompleted todos'. This is a query/retrieval operation with no side effects.
Attacks that exploit this kind of access
获取所有到期且未完成的待办事项. It is categorised as a Read tool in the MCP Reminder MCP Server, which means it retrieves data without modifying state.
Register the MCP Reminder MCP server in PolicyLayer and add a rule for get_pending_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 MCP Reminder. Nothing to install.
get_pending_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_pending_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_pending_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_pending_todos is provided by the MCP Reminder MCP server (sheacoding/mcp-reminder). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →