List all tasks Use when native TodoWrite is wrong because you need cross-session task persistence, agent assignment, dependency tracking, or completion analytics in the .swarm/memory.db. For in-session checklists native TodoWrite is simpler and faster.
AI agents call task_list to retrieve information from Claude Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries task data from a database without creating, modifying, deleting, or executing operations. It is purely informational, comparing favorably to native TodoWrite for cross-session visibility. The blast radius of misuse is minimal—an agent could only waste context or expose task metadata it shouldn't see, not cause data loss or harmful side effects.
From the tool's definition Tool name is 'task_list' and description explicitly states 'List all tasks' with no mutation operations mentioned.
Attacks that exploit this kind of access
List all tasks Use when native TodoWrite is wrong because you need cross-session task persistence, agent assignment, dependency tracking, or completion analytics in the .swarm/memory.db. For in-session checklists native TodoWrite is simpler and faster. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.
Register the Claude Flow MCP server in PolicyLayer and add a rule for task_list: 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 Claude Flow. Nothing to install.
task_list 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 task_list 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 task_list. 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.
task_list is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.