Create an index on a node label
AI agents use neo4j.create_index to create or update resources in Neo4j MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Neo4j MCP Server environment.
Creating an index modifies the database schema and structure, which is a Write operation—it creates new metadata but is reversible (indexes can be dropped). The operation does not delete data (not Destructive), execute arbitrary code (not Execute), involve financial transactions (not Financial), or merely read data (not Read).
From the tool's definition Tool name 'create_index' and description 'Create an index on a node label' indicate a schema modification operation that creates a new database index structure.
Attacks that exploit this kind of access
Create an index on a node label. It is categorised as a Write tool in the Neo4j MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Neo4j MCP Server MCP server in PolicyLayer and add a rule for neo4j.create_index: 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 Neo4j MCP Server. Nothing to install.
neo4j.create_index 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 neo4j.create_index 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 neo4j.create_index. 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.
neo4j.create_index is provided by the Neo4j MCP Server MCP server (vpro1032/neo4j-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 →