Execute OData queries on relational entities for ETL data extraction. Supports large batch processing (up to 50,000 records), advanced filtering, column selection, and pagination. Optimized for data warehouse loading and analytics pipelines. Use list_relational_entities to discover available enti...
AI agents invoke query_relational_entity to trigger actions in SAP Datasphere MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool executes OData queries against a production SAP Datasphere environment. While primarily used for data extraction (read-like), it 'executes' queries with advanced filtering and large-scale data access. The blast radius is high because misuse could exfiltrate up to 50,000 records per batch from a production data warehouse, exposing sensitive enterprise data.
From the tool's definition "Execute OData queries on relational entities for ETL data extraction" and "large batch processing (up to 50,000 records), advanced filtering, column selection, and pagination"
Documented attack patterns abuse exactly the kind of access query_relational_entity gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SAP Datasphere MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for query_relational_entity:
{
"version": "1",
"default": "deny",
"tools": {
"query_relational_entity": {
"limits": [
{
"counter": "query_relational_entity_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}query_relational_entity stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute OData queries on relational entities for ETL data extraction. Supports large batch processing (up to 50,000 records), advanced filtering, column selection, and pagination. Optimized for data warehouse loading and analytics pipelines. Use list_relational_entities to discover available entity names first. It is categorised as a Execute tool in the SAP Datasphere MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the SAP Datasphere MCP Server MCP server in PolicyLayer and add a rule for query_relational_entity: 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 SAP Datasphere MCP Server. Nothing to install.
query_relational_entity is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the query_relational_entity 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 query_relational_entity. 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.
query_relational_entity is provided by the SAP Datasphere MCP Server MCP server (mariodefelipe/sap-datasphere-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SAP Datasphere MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
31 SAP Datasphere MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.