continue_task
Continue a stopped or running task with additional input/instructions. Pass device_id to inject the follow-up into a task running on another device's daemon.
This record as markdown: /tools/io-github-kivanccakmak-yaver/continue-task.md
What continue_task does on Yaver
AI agents invoke continue_task to trigger actions in Yaver. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
input | string | Yes | Follow-up instructions for the task |
task_id | string | Yes | The task ID to continue |
device_id | string | — | Optional: target device whose daemon runs the task (omit for the local machine) |
Parameters from the server's own tool schema.
Why continue_task is rated High
This tool resumes or modifies execution of an active task, potentially on a remote device's daemon. It triggers external operations whose effects depend on the injected instructions. The ability to inject instructions into another device's running daemon significantly raises the blast radius, as it could execute arbitrary build, deploy, or shell operations on remote systems.
From the tool's definition "Continue a stopped or running task with additional input/instructions" and "inject the follow-up into a task running on another device's daemon"
Attacks that exploit this kind of access
The rule that runs continue_task safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Yaver, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For continue_task, this is the rule to start with:
continue_task stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Yaver, apply this rule, and every continue_task call is checked against it from then on.
Questions about continue_task
Continue a stopped or running task with additional input/instructions. Pass device_id to inject the follow-up into a task running on another device's daemon. It is categorised as a Execute tool in the Yaver MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
continue_task accepts 3 parameters: input, task_id, device_id. Required: input, task_id. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for continue_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 Yaver. Nothing to install.
continue_task is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the continue_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 continue_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.
continue_task is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Yaver, and thousands of servers like it.
Across the catalogue