列出所有待办条目。每次开始工作前调用，了解还有哪些未完成事项。
AI agents call project_doc_todos to retrieve information from ProjectDoc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays existing todo data without creating, modifying, deleting, or executing any operations. It has no side effects and presents information only. This is a classic Read category tool. Low severity because viewing todo items cannot cause harm even if an AI agent misuses it—worst case is accessing non-sensitive task information.
From the tool's definition Tool name 'project_doc_todos' and description 'lists all todo items' indicates a retrieval/query operation. The Chinese description translates to 'List all todo items.
Attacks that exploit this kind of access
列出所有待办条目。每次开始工作前调用，了解还有哪些未完成事项。. It is categorised as a Read tool in the ProjectDoc MCP Server, which means it retrieves data without modifying state.
Register the ProjectDoc MCP server in PolicyLayer and add a rule for project_doc_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 ProjectDoc. Nothing to install.
project_doc_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 project_doc_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 project_doc_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.
project_doc_todos is provided by the ProjectDoc MCP server (yarrow-cai/project-doc). 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 →