Get all registered AI model endpoints from seekdb. Returns: str: JSON string containing the list of AI model endpoints with fields: - ENDPOINT_ID: Endpoint identifier - ENDPOINT_NAME: Name of the endpoint - AI_MODEL_NAME: Associated AI model name - SCOPE: Scope of the endpoint - URL: URL of the A...
AI agents call get_ai_model_endpoints to retrieve information from Mcp Oceanbase without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation—it retrieves and queries existing data without modifying or deleting anything. However, severity is elevated to medium because the returned data includes sensitive information (ACCESS_KEY fields marked as encrypted, provider credentials, and model service URLs), which could be leveraged by an attacker to access external AI services or understand the system's AI infrastructure.
From the tool's definition Tool name 'get_ai_model_endpoints' with description 'Get all registered AI model endpoints from seekdb' indicates retrieval of configuration data.
Documented attack patterns abuse exactly the kind of access get_ai_model_endpoints 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 get_ai_model_endpoints:
{
"version": "1",
"default": "deny",
"tools": {
"get_ai_model_endpoints": {}
}
}get_ai_model_endpoints is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get all registered AI model endpoints from seekdb. Returns: str: JSON string containing the list of AI model endpoints with fields: - ENDPOINT_ID: Endpoint identifier - ENDPOINT_NAME: Name of the endpoint - AI_MODEL_NAME: Associated AI model name - SCOPE: Scope of the endpoint - URL: URL of the AI model service - ACCESS_KEY: Access key (encrypted) - PROVIDER: Provider name (e.g., openai, siliconflow) - REQUEST_MODEL_NAME: Model name used in requests - PARAMETERS: Additional parameters - REQUEST_TRANSFORM_FN: Request transformation function - RESPONSE_TRANSFORM_FN: Response transformation function. It is categorised as a Read tool in the Mcp Oceanbase MCP Server, which means it retrieves data without modifying state.
Register the Mcp Oceanbase MCP server in PolicyLayer and add a rule for get_ai_model_endpoints: 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.
get_ai_model_endpoints 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 get_ai_model_endpoints 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 get_ai_model_endpoints. 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.
get_ai_model_endpoints 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.