人間アクションリストを管理する。AIが解決できなかったタスクの一覧表示と対応操作。 操作モード: - mode=
AI agents call task_action_list to retrieve information from Wasurenagusa without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'task_action_list' and the description's emphasis on '一覧表示' (listing/displaying) suggests a Read operation for viewing human action items. However, the description is cut off after 'mode=' which suggests there may be additional modes beyond just listing. Given the truncation lowers confidence, I classify as Read based on available evidence, but acknowledge write/execute modes may exist.
From the tool's definition Tool description mentions '一覧表示' (list display) of tasks that AI could not resolve, and '管理する' (manage). The description is truncated after 'mode=' leaving the actual operations unclear.
Attacks that exploit this kind of access
人間アクションリストを管理する。AIが解決できなかったタスクの一覧表示と対応操作。 操作モード: - mode=. It is categorised as a Read tool in the Wasurenagusa MCP Server, which means it retrieves data without modifying state.
Register the Wasurenagusa MCP server in PolicyLayer and add a rule for task_action_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 Wasurenagusa. Nothing to install.
task_action_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_action_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_action_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_action_list is provided by the Wasurenagusa MCP server (tsutushi0628/wasurenagusa-mcp). 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 →