获取用户的待办，返回给用户的时候需要说明这是待办
AI agents call get_todo to retrieve information from TAPD MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool fetches and displays pending tasks/to-do items without creating, modifying, or deleting any data. It has no side effects beyond data retrieval. The low severity reflects minimal blast radius—misuse would only expose or retrieve existing to-do information that the authenticated user likely already has access to.
From the tool's definition get_todo retrieves user's to-do items (待办). The 'get' prefix and retrieval semantics indicate a read-only query with no modification or deletion of data.
Attacks that exploit this kind of access
获取用户的待办，返回给用户的时候需要说明这是待办. It is categorised as a Read tool in the TAPD MCP Server MCP Server, which means it retrieves data without modifying state.
Register the TAPD MCP Server MCP server in PolicyLayer and add a rule for get_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 TAPD MCP Server. Nothing to install.
get_todo 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_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 get_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.
get_todo is provided by the TAPD MCP Server MCP server (ken19990709/mcp-server-for-tapd). 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 →