This record as markdown: /tools/funny-booth-aos-mcp-server/reject-task.md
What reject_task does on Aos
AI agents use reject_task to create or update resources in Aos, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Aos environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
id | string | Yes | タスクID |
note | string | — | 却下理由 |
Parameters from the server's own tool schema.
Why reject_task is rated Medium
This tool appears to perform a reversible state change on a task object (likely marking it as rejected). This is a Write operation—it modifies data without permanent deletion and can typically be undone by changing the task status again. Severity is medium because rejecting tasks could disrupt workflows or project timelines, but the effect is recoverable.
From the tool's definition Tool name 'reject_task' indicates modification of task state; sibling tools include 'complete_task', 'create_task', and other CRUD operations suggesting this server manages task/workflow objects.
Attacks that exploit this kind of access
The rule that runs reject_task safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Aos, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For reject_task, this is the rule to start with:
reject_task stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Aos, apply this rule, and every reject_task call is checked against it from then on.
Questions about reject_task
reject_task is a write tool on the Aos MCP server. It is categorised as a Write tool in the Aos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
reject_task accepts 2 parameters: id, note. Required: id. The full parameter table on this page comes from the server's own tool schema.
Register the Aos MCP server in PolicyLayer and add a rule for reject_task: 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 Aos. Nothing to install.
reject_task is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the reject_task 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 reject_task. 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.
reject_task is provided by the Aos MCP server (@funny-booth/aos-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Aos, and thousands of servers like it.
This server
Across the catalogue