This record as markdown: /tools/3xcaffeine-mcp-server/list-task-lists.md
What list_task_lists does on VaultAssist
AI agents call list_task_lists to retrieve information from VaultAssist without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why list_task_lists is rated Low
This tool retrieves task list metadata for the authenticated user. It performs a read-only query operation with no side effects, no data modification, and no execution of arbitrary commands. The blast radius of misuse is minimal — an attacker could enumerate a user's tasks but cannot modify, delete, or exfiltrate them through this tool alone.
From the tool's definition 'List all task lists for the user' — a retrieval operation that queries task data without modification, deletion, or execution of external code.
Attacks that exploit this kind of access
The rule that runs list_task_lists safely
PolicyLayer is an MCP gateway: it sits between your AI agents and VaultAssist, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For list_task_lists, this is the rule to start with:
list_task_lists is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect VaultAssist, apply this rule, and every list_task_lists call is checked against it from then on.
Questions about list_task_lists
List all task lists for the user. It is categorised as a Read tool in the VaultAssist MCP Server, which means it retrieves data without modifying state.
Register the VaultAssist MCP server in PolicyLayer and add a rule for list_task_lists: 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 VaultAssist. Nothing to install.
list_task_lists 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_task_lists 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_task_lists. 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_task_lists is provided by the VaultAssist MCP server (3xcaffeine/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on VaultAssist, and thousands of servers like it.
This server
Across the catalogue