ai_ultra
LLM completion (ultra tier, Claude Opus 4.6) — the top-end reasoning model for the hardest agent tasks: deep multi-step analysis and high-stakes drafting. Pay USDC per call, no API key. Use when model quality dominates cost. Example call: {"prompt": "Reason step by step about this complex case: ....
This record as markdown: /tools/io-github-colinhughes2121-gocreative-agent-api/ai-ultra.md
What ai_ultra does on GoCreative Agent API
AI agents call ai_ultra to retrieve information from GoCreative Agent API without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Yes |
Parameters from the server's own tool schema.
Why ai_ultra is rated Low
Even though ai_ultra only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs ai_ultra safely
PolicyLayer is an MCP gateway: it sits between your AI agents and GoCreative Agent API, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For ai_ultra, this is the rule to start with:
ai_ultra is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect GoCreative Agent API, apply this rule, and every ai_ultra call is checked against it from then on.
Questions about ai_ultra
LLM completion (ultra tier, Claude Opus 4.6) — the top-end reasoning model for the hardest agent tasks: deep multi-step analysis and high-stakes drafting. Pay USDC per call, no API key. Use when model quality dominates cost. Example call: {"prompt": "Reason step by step about this complex case: ..."} Cost: $0.005–$0.05 USDC on Base per call. It is categorised as a Read tool in the GoCreative Agent API MCP Server, which means it retrieves data without modifying state.
ai_ultra accepts 1 parameter: prompt. Required: prompt. The full parameter table on this page comes from the server's own tool schema.
Register the GoCreative Agent API MCP server in PolicyLayer and add a rule for ai_ultra: 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 GoCreative Agent API. Nothing to install.
ai_ultra 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 ai_ultra 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 ai_ultra. 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.
ai_ultra is provided by the GoCreative Agent API MCP server (https://api.gocreativeai.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on GoCreative Agent API, and thousands of servers like it.
This server
Across the catalogue