AI agents call get_tasks_tool to retrieve information from TaskMaster without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or lists tasks from Todoist with no side effects. It is a Read operation—purely informational access to existing data. The severity is low because task retrieval poses minimal risk; an agent can read but not modify or delete tasks. Confidence is high based on the clear naming pattern and server context, though the empty description slightly reduces certainty.
From the tool's definition Tool name 'get_tasks_tool' indicates a retrieval operation. The server description states it 'enables Cursor AI assistants to interact with Todoist tasks' and mentions 'advanced task filtering,' confirming this tool queries/retrieves task data.
Documented attack patterns abuse exactly the kind of access get_tasks_tool gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and TaskMaster, and nothing reaches the server without passing your rules. This is the rule we recommend for get_tasks_tool:
{
"version": "1",
"default": "deny",
"tools": {
"get_tasks_tool": {}
}
}get_tasks_tool 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.
get_tasks_tool. It is categorised as a Read tool in the TaskMaster MCP Server, which means it retrieves data without modifying state.
Register the TaskMaster MCP server in PolicyLayer and add a rule for get_tasks_tool: 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 TaskMaster. Nothing to install.
get_tasks_tool 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_tasks_tool 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_tasks_tool. 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_tasks_tool is provided by the TaskMaster MCP server (mingolladaniele/taskmaster-todoist-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from TaskMaster, 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.
3 TaskMaster tools catalogued and risk-classified — across an index of 43,000+ MCP servers.