Get a list of all pending tasks
AI agents call get_next_tasks to retrieve information from Taskwarrior without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns a list of pending tasks without modifying, deleting, or executing any operations. It is a straightforward read operation that retrieves data from taskwarrior. The low severity reflects minimal risk if misused by an agent, as the only potential harm is information disclosure of task contents.
From the tool's definition Tool name 'get_next_tasks' and description 'Get a list of all pending tasks' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get a list of all pending tasks. It is categorised as a Read tool in the Taskwarrior MCP Server, which means it retrieves data without modifying state.
Register the Taskwarrior MCP server in PolicyLayer and add a rule for get_next_tasks: 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 Taskwarrior. Nothing to install.
get_next_tasks 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_next_tasks 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_next_tasks. 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_next_tasks is provided by the Taskwarrior MCP server (mcp-server-taskwarrior). 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 →