Query the cardiology knowledge graph with natural language.
AI agents call query_graph to retrieve information from Cardiology Knowledge Graph MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information from the knowledge graph using natural language queries. It does not create, modify, or delete data—it only reads/searches existing data. While the underlying knowledge graph contains medical information, the tool itself has no side effects beyond returning query results.
From the tool's definition Tool name is 'query_graph' and description states it performs 'Query the cardiology knowledge graph with natural language.' The verb 'query' with the stated capability of performing lookups indicates retrieval-only operations without modification.
Attacks that exploit this kind of access
Query the cardiology knowledge graph with natural language. It is categorised as a Read tool in the Cardiology Knowledge Graph MCP MCP Server, which means it retrieves data without modifying state.
Register the Cardiology Knowledge Graph MCP server in PolicyLayer and add a rule for query_graph: 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 Cardiology Knowledge Graph MCP. Nothing to install.
query_graph 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 query_graph 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_graph. 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_graph is provided by the Cardiology Knowledge Graph MCP server (ryoureddy/cardiology-knowledge-graph-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 →