AI agents use create_ai_model to create or update resources in Mcp Oceanbase — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Oceanbase environment.
The name suggests creating an AI model resource, which is a Write operation (creating a new entity). However, with no description available, confidence is reduced. Based on sibling tools like 'add_memory', 'ai_complete', and 'ai_rerank', this server deals with AI/ML operations, supporting the interpretation that this tool creates a model configuration or resource.
From the tool's definition Tool name 'create_ai_model' — description is empty or uninformative.
Documented attack patterns abuse exactly the kind of access create_ai_model gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Oceanbase, and nothing reaches the server without passing your rules. This is the rule we recommend for create_ai_model:
{
"version": "1",
"default": "deny",
"tools": {
"create_ai_model": {
"limits": [
{
"counter": "create_ai_model_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_ai_model 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.
create_ai_model. It is categorised as a Write tool in the Mcp Oceanbase MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Oceanbase MCP server in PolicyLayer and add a rule for create_ai_model: 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 Mcp Oceanbase. Nothing to install.
create_ai_model 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 create_ai_model 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 create_ai_model. 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.
create_ai_model is provided by the Mcp Oceanbase MCP server (oceanbase/awesome-oceanbase-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 134 Mcp Oceanbase tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
134 Mcp Oceanbase tools catalogued and risk-classified — across an index of 42,500+ MCP servers.