Submit a task to a real human operator via the Callable network. Use this when your agent cannot complete an action autonomously — such as making a phone call, recording a face-cam UGC video, filling a form that requires real identity, verifying an account, or posting authentically on social medi...
Risk signalsAccepts URL/endpoint input (callback_url)
Part of the Callable server.
Free to start. No card required.
AI agents use submit_task to create or modify resources in Callable. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call submit_task repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Callable.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"submit_task": {
"limits": [
{
"counter": "submit_task_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Callable policy for all 3 tools.
These attack patterns abuse exactly the kind of access submit_task gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Submit a task to a real human operator via the Callable network. Use this when your agent cannot complete an action autonomously — such as making a phone call, recording a face-cam UGC video, filling a form that requires real identity, verifying an account, or posting authentically on social media. The task is charged automatically via Stripe. A human operator claims and completes it within the deadline. The result is delivered to your callback_url or retrievable via get_task_status.. It is categorised as a Write tool in the Callable MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Callable 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 Callable. Nothing to install.
submit_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 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 Callable MCP server (https://getcallable.dev/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 Callable tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.