Approve a pending or blocked task, marking it complete. This is used for approval gates - when a task is awaiting human sign-off before proceeding. Args: task_id: ID of the task to approve. note: Optional approval note recorded as the result summary. Returns: JSON with the updated task status.
AI agents use bernstein_approve to create or update resources in Bernstein - Multi-agent orchestration — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Bernstein - Multi-agent orchestration environment.
This tool creates or modifies data (task status) reversibly. While it has workflow automation implications, it does not execute arbitrary code, delete data irreversibly, or move money. The 'high' severity reflects that approving tasks in an AI coding agent orchestration system could advance potentially problematic code changes or deployments if misused, but the action itself is Write-category (state modification).
From the tool's definition Approve a pending or blocked task, marking it complete. The tool modifies task state by marking tasks as complete and updates task status, which is a reversible state change in the workflow orchestration system.
Documented attack patterns abuse exactly the kind of access bernstein_approve gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Bernstein - Multi-agent orchestration, and nothing reaches the server without passing your rules. This is the rule we recommend for bernstein_approve:
{
"version": "1",
"default": "deny",
"tools": {
"bernstein_approve": {
"limits": [
{
"counter": "bernstein_approve_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}bernstein_approve stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Approve a pending or blocked task, marking it complete. This is used for approval gates - when a task is awaiting human sign-off before proceeding. Args: task_id: ID of the task to approve. note: Optional approval note recorded as the result summary. Returns: JSON with the updated task status. It is categorised as a Write tool in the Bernstein - Multi-agent orchestration MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Bernstein - Multi-agent orchestration MCP server in PolicyLayer and add a rule for bernstein_approve: 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 Bernstein - Multi-agent orchestration. Nothing to install.
bernstein_approve 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 bernstein_approve 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 bernstein_approve. 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.
bernstein_approve is provided by the Bernstein - Multi-agent orchestration MCP server (sipyourdrink-ltd/bernstein). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 12 Bernstein - Multi-agent orchestration tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
12 Bernstein - Multi-agent orchestration tools catalogued and risk-classified — across an index of 42,500+ MCP servers.