Create a new graph in the AGE
AI agents use create-age-graph to create or update resources in AGE-MCP-Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AGE-MCP-Server environment.
This tool creates a new graph entity in the AGE (Apache AGE) graph database, which is a reversible write operation. While it modifies the database state by adding a new graph, it can be undone by deleting the graph afterward. It does not execute arbitrary code, delete existing data irreversibly, or involve financial transactions.
From the tool's definition Tool name and description indicate it 'Create a new graph in the AGE' — a create operation that adds new data structure to the graph database.
Attacks that exploit this kind of access
Create a new graph in the AGE. It is categorised as a Write tool in the AGE-MCP-Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AGE-MCP-Server MCP server in PolicyLayer and add a rule for create-age-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 AGE-MCP-Server. Nothing to install.
create-age-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 create-age-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 create-age-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.
create-age-graph is provided by the AGE-MCP-Server MCP server (rioriost/age_mcp_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 →