Escalate an A2A task for human review through HITL. Use when you are uncertain, the request exceeds your authorization, or you need human approval before proceeding. The task is held until a human reviews and responds.
Part of the AgentTrust — Identity & Trust for A2A Agents server.
Free to start. No card required.
AI agents use agenttrust_escalate to create or modify resources in AgentTrust — Identity & Trust for A2A Agents. 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 agenttrust_escalate 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 AgentTrust — Identity & Trust for A2A Agents.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"agenttrust_escalate": {
"limits": [
{
"counter": "agenttrust_escalate_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full AgentTrust — Identity & Trust for A2A Agents policy for all 19 tools.
These attack patterns abuse exactly the kind of access agenttrust_escalate 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.
Escalate an A2A task for human review through HITL. Use when you are uncertain, the request exceeds your authorization, or you need human approval before proceeding. The task is held until a human reviews and responds.. It is categorised as a Write tool in the AgentTrust — Identity & Trust for A2A Agents MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AgentTrust — Identity & Trust for A2A Agents MCP server in PolicyLayer and add a rule for agenttrust_escalate: 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 AgentTrust — Identity & Trust for A2A Agents. Nothing to install.
agenttrust_escalate 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 agenttrust_escalate 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 agenttrust_escalate. 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.
agenttrust_escalate is provided by the AgentTrust — Identity & Trust for A2A Agents MCP server (@agenttrust/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 19 AgentTrust — Identity & Trust for A2A Agents 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.