Add finalized entities/relationships JSON to the Neo4j knowledge graph.
AI agents use add_to_graph to create or update resources in Cardiology Knowledge Graph MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cardiology Knowledge Graph MCP environment.
This tool creates or modifies data in a Neo4j graph database by adding medical entities and relationships. It is reversible (data can be corrected, deleted, or updated in subsequent operations), making it a Write rather than Destructive action.
From the tool's definition Tool description states 'Add finalized entities/relationships JSON to the Neo4j knowledge graph.' The verb 'add' and action of inserting data into a database constitutes data modification.
Attacks that exploit this kind of access
Add finalized entities/relationships JSON to the Neo4j knowledge graph. It is categorised as a Write tool in the Cardiology Knowledge Graph MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cardiology Knowledge Graph MCP server in PolicyLayer and add a rule for add_to_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.
add_to_graph is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_to_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 add_to_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.
add_to_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 →