sandboxes_agent_tasks_deliver
Run sandboxes.agent-tasks.deliver through the Appaloft application operation catalog. Shared with CLI and HTTP/API.
This record as markdown: /tools/appaloft-mcp/sandboxes-agent-tasks-deliver.md
What sandboxes_agent_tasks_deliver does on Appaloft
AI agents invoke sandboxes_agent_tasks_deliver to trigger actions in Appaloft. 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 |
|---|---|---|---|
branch | string | Yes | |
remote | string | — | |
taskRunId | string | Yes | |
pullRequest | object | — | |
workspaceId | string | Yes | |
commitMessage | string | Yes |
Parameters from the server's own tool schema.
Why sandboxes_agent_tasks_deliver is rated High
sandboxes_agent_tasks_deliver triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Risk signalsAccepts raw HTML/template content (pullRequest.body) · High parameter count (10 properties)
Attacks that exploit this kind of access
The rule that runs sandboxes_agent_tasks_deliver safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Appaloft, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For sandboxes_agent_tasks_deliver, this is the rule to start with:
sandboxes_agent_tasks_deliver 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 Appaloft, apply this rule, and every sandboxes_agent_tasks_deliver call is checked against it from then on.
Questions about sandboxes_agent_tasks_deliver
Run sandboxes.agent-tasks.deliver through the Appaloft application operation catalog. Shared with CLI and HTTP/API. It is categorised as a Execute tool in the Appaloft MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
sandboxes_agent_tasks_deliver accepts 6 parameters: branch, remote, taskRunId, pullRequest, workspaceId, commitMessage. Required: branch, taskRunId, workspaceId, commitMessage. The full parameter table on this page comes from the server's own tool schema.
Register the Appaloft MCP server in PolicyLayer and add a rule for sandboxes_agent_tasks_deliver: 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 Appaloft. Nothing to install.
sandboxes_agent_tasks_deliver 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 sandboxes_agent_tasks_deliver 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 sandboxes_agent_tasks_deliver. 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.
sandboxes_agent_tasks_deliver is provided by the Appaloft MCP server (@appaloft/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Appaloft, and thousands of servers like it.
Across the catalogue