Reply to a question from the Agentwork agent. Use this when agentwork_get_task_status returns status "awaiting_reply". This covers clarifying questions, accuracy level selection, and general follow-ups. Args: task_id: The task ID. message: Your reply to the agent's question. api_key: Your Agentwo...
Risk signalsHandles credentials or secrets (api_key)
Part of the Agentwork server.
Free to start. No card required.
AI agents use agentwork_send_message to create or modify resources in Agentwork. 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 agentwork_send_message 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 Agentwork.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"agentwork_send_message": {
"limits": [
{
"counter": "agentwork_send_message_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Agentwork policy for all 9 tools.
These attack patterns abuse exactly the kind of access agentwork_send_message 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.
Reply to a question from the Agentwork agent. Use this when agentwork_get_task_status returns status "awaiting_reply". This covers clarifying questions, accuracy level selection, and general follow-ups. Args: task_id: The task ID. message: Your reply to the agent's question. api_key: Your Agentwork API key. Returns: JSON with success status.. It is categorised as a Write tool in the Agentwork MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Agentwork MCP server in PolicyLayer and add a rule for agentwork_send_message: 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 Agentwork. Nothing to install.
agentwork_send_message 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 agentwork_send_message 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 agentwork_send_message. 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.
agentwork_send_message is provided by the Agentwork MCP server (agentwork-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 9 Agentwork 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.