This query retrieves all entity types in the RDF graph, along with their labels and comments if available.
AI agents call podbc_sparql_list_entity_types_detailed to retrieve information from MCP PyODBC Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a query operation that returns metadata about entity types without modifying any data. However, it is classified as medium severity rather than low because: (1) it operates on database/RDF systems where information disclosure could be sensitive, (2) it could expose the full schema/structure of an RDF graph which might include proprietary data models, and (3) when combined with other tools on this…
From the tool's definition The tool description explicitly states it 'retrieves all entity types in the RDF graph, along with their labels and comments if available.' The verb 'retrieves' and the read-only nature of querying RDF metadata indicate no data modification or side effects.
Attacks that exploit this kind of access
This query retrieves all entity types in the RDF graph, along with their labels and comments if available. It is categorised as a Read tool in the MCP PyODBC Server MCP Server, which means it retrieves data without modifying state.
Register the MCP PyODBC Server MCP server in PolicyLayer and add a rule for podbc_sparql_list_entity_types_detailed: 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 PyODBC Server. Nothing to install.
podbc_sparql_list_entity_types_detailed 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 podbc_sparql_list_entity_types_detailed 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 podbc_sparql_list_entity_types_detailed. 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.
podbc_sparql_list_entity_types_detailed is provided by the MCP PyODBC Server MCP server (openlinksoftware/mcp-pyodbc-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →