Pick the best option from a set of variants (Multi-Armed Bandit: UCB1, Thompson sampling, or ε-greedy). Use this when you have N options with observed reward history and need to choose the next one with optimal explore/exploit tradeoff (A/B test arm selection, ad/email variant routing, recommenda...
Part of the Oraclaw server.
Free to start. No card required.
AI agents use optimize_bandit to create or modify resources in Oraclaw. 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 optimize_bandit 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 Oraclaw.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"optimize_bandit": {
"limits": [
{
"counter": "optimize_bandit_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Oraclaw policy for all 17 tools.
These attack patterns abuse exactly the kind of access optimize_bandit 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.
Pick the best option from a set of variants (Multi-Armed Bandit: UCB1, Thompson sampling, or ε-greedy). Use this when you have N options with observed reward history and need to choose the next one with optimal explore/exploit tradeoff (A/B test arm selection, ad/email variant routing, recommendation ranking). For context-dependent selection (different best option per user/situation), use optimize_contextual instead. For continuous parameter tuning, use optimize_cmaes. Returns the selected arm + score breakdown in <1ms.. It is categorised as a Write tool in the Oraclaw MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Oraclaw MCP server in PolicyLayer and add a rule for optimize_bandit: 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 Oraclaw. Nothing to install.
optimize_bandit 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 optimize_bandit 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 optimize_bandit. 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.
optimize_bandit is provided by the Oraclaw MCP server (@oraclaw/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 17 Oraclaw 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.