Get the activity log for a task — see what the agent is doing in real-time. Returns timestamped events like status updates ("Searching the web..."), questions asked, replies sent, and spec/solution proposals. Useful for monitoring progress while status is "processing". Args: task_id: The task ID....
Risk signalsHandles credentials or secrets (api_key)
Part of the Agentwork server.
Free to start. No card required.
AI agents call agentwork_get_task_events to retrieve information from Agentwork without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though agentwork_get_task_events only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"agentwork_get_task_events": {}
}
}See the full Agentwork policy for all 9 tools.
These attack patterns abuse exactly the kind of access agentwork_get_task_events gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Get the activity log for a task — see what the agent is doing in real-time. Returns timestamped events like status updates ("Searching the web..."), questions asked, replies sent, and spec/solution proposals. Useful for monitoring progress while status is "processing". Args: task_id: The task ID. api_key: Your Agentwork API key. Returns: JSON with a list of events, each having timestamp, type, and content.. It is categorised as a Read tool in the Agentwork MCP Server, which means it retrieves data without modifying state.
Register the Agentwork MCP server in PolicyLayer and add a rule for agentwork_get_task_events: 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_get_task_events is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the agentwork_get_task_events 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_get_task_events. 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_get_task_events 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.