Find classes in the ontology. Can filter by name pattern.
AI agents call search_classes to retrieve information from RDF4J MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves ontology metadata without modifying, executing code, deleting, or committing financial transactions. It is a read-only query operation that explores RDF/ontology structure, fitting the Read category for data retrieval with no side effects.
From the tool's definition Tool description states 'Find classes in the ontology. Can filter by name pattern.' The verb 'find' and the filtering capability indicate a search/query operation with no side effects.
Attacks that exploit this kind of access
Find classes in the ontology. Can filter by name pattern. It is categorised as a Read tool in the RDF4J MCP Server MCP Server, which means it retrieves data without modifying state.
Register the RDF4J MCP Server MCP server in PolicyLayer and add a rule for search_classes: 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 RDF4J MCP Server. Nothing to install.
search_classes 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 search_classes 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 search_classes. 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.
search_classes is provided by the RDF4J MCP Server MCP server (odysa/rdf4j-mcp). 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 →