multi_graph_query
AI agents call multi_graph_query to retrieve information from MCP Server Proto-OKN without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool querying multiple SPARQL graphs is primarily a Read operation—it retrieves data from knowledge graphs without side effects. However, complexity of multi-graph SPARQL queries and potential for resource exhaustion or information disclosure across graphs elevates severity from low to medium. The empty description creates minor confidence reduction.
From the tool's definition Tool name 'multi_graph_query' and server context indicate querying SPARQL endpoints against knowledge graphs. Sibling tools include 'query', 'get_schema', and 'list_graphs', all read operations. Description is empty, lowering confidence slightly.
Attacks that exploit this kind of access
multi_graph_query. It is categorised as a Read tool in the MCP Server Proto-OKN MCP Server, which means it retrieves data without modifying state.
Register the MCP Server Proto-OKN MCP server in PolicyLayer and add a rule for multi_graph_query: 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 Server Proto-OKN. Nothing to install.
multi_graph_query 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 multi_graph_query 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 multi_graph_query. 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.
multi_graph_query is provided by the MCP Server Proto-OKN MCP server (sbl-sdsc/mcp-proto-okn). 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 →