This query retrieves samples of entities for each type in the RDF graph, along with their labels and counts. It groups by entity type and orders the results by sample count in descending order. Note: The LIMIT clause is set to 20 to restrict the number of entity types returned.
AI agents call sparql_list_entity_types_samples to retrieve information from Mcp Odbc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a SELECT-style query that retrieves and displays data (samples of entities, labels, counts) from an RDF graph without creating, modifying, deleting, or executing any operations. It has no side effects and fits the 'Read' category as a data retrieval operation.
From the tool's definition Tool description explicitly states it 'retrieves samples' and 'orders the results' without mentioning any modification, deletion, or execution of external operations. The SPARQL query is read-only, fetching entity type information from an RDF graph.
Documented attack patterns abuse exactly the kind of access sparql_list_entity_types_samples gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Odbc, and nothing reaches the server without passing your rules. This is the rule we recommend for sparql_list_entity_types_samples:
{
"version": "1",
"default": "deny",
"tools": {
"sparql_list_entity_types_samples": {}
}
}sparql_list_entity_types_samples 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.
This query retrieves samples of entities for each type in the RDF graph, along with their labels and counts. It groups by entity type and orders the results by sample count in descending order. Note: The LIMIT clause is set to 20 to restrict the number of entity types returned. It is categorised as a Read tool in the Mcp Odbc MCP Server, which means it retrieves data without modifying state.
Register the Mcp Odbc MCP server in PolicyLayer and add a rule for sparql_list_entity_types_samples: 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 Odbc. Nothing to install.
sparql_list_entity_types_samples 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 sparql_list_entity_types_samples 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 sparql_list_entity_types_samples. 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.
sparql_list_entity_types_samples is provided by the Mcp Odbc MCP server (openlinksoftware/mcp-odbc-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Odbc, 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.
15 Mcp Odbc tools catalogued and risk-classified — across an index of 43,000+ MCP servers.