AI agents invoke submit_task to trigger actions in Unlimited. 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.
The server description clearly indicates this MCP server submits tasks to background agents that perform coding and sysops work. 'submit_task' likely submits such a task for execution. This falls under Execute as it triggers external operations. The description is empty, lowering confidence, but sibling tools like 'add_queue', 'await_job', 'cancel_job' strongly suggest a job/task execution pipeline.
From the tool's definition Tool name 'submit_task' combined with server description mentioning 'delegates coding and sysops work to cheaper agents via durable background queues, with git worktree isolation, safety policies'
Attacks that exploit this kind of access
submit_task. It is categorised as a Execute tool in the Unlimited MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Unlimited MCP server in PolicyLayer and add a rule for submit_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 Unlimited. Nothing to install.
submit_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 submit_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 submit_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.
submit_task is provided by the Unlimited MCP server (triumsebas/unlimited-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 →