AI agents use create-tables to create or update resources in Neosql — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Neosql environment.
Creating tables is a Write operation—it modifies the database structure but is reversible (tables can be dropped). While it affects schema, it doesn't execute arbitrary code (Execute), delete data (Destructive), or move money (Financial). The medium severity reflects that schema changes can have operational impact but are generally reversible and don't cause data loss by themselves.
From the tool's definition Tool name is 'create-tables' and description states it will 'Create one or more new tables in the NeoSQL application.' This is a data creation operation that modifies the database schema reversibly.
Attacks that exploit this kind of access
Create one or more new tables in the NeoSQL application. It is categorised as a Write tool in the Neosql MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Neosql MCP server in PolicyLayer and add a rule for create-tables: 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 Neosql. Nothing to install.
create-tables 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-tables 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-tables. 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-tables is provided by the Neosql MCP server (unvus/neosql-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 →