create_database · PySqlit MCP: Risk & Policy

WHAT IT DOES

What create_database does on PySqlitMCP

AI agents use create_database to create or update resources in PySqlitMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your PySqlitMCP environment.

WHY IT NEEDS A POLICY

Why create_database needs a policy

Creating a database is a reversible write operation—it establishes a new data structure but can be undone by deleting the database. This is less severe than destructive operations (which permanently erase data) but more severe than simple reads. The high severity reflects the blast radius: an AI agent could create numerous unwanted databases, consuming storage and potentially overwriting critical infrastructure.

From the tool's definition Tool name 'create_database' combined with server description stating 'database creation' and 'data CRUD operations' indicates the tool creates new databases.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_database Rate-limited

create_database stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_database": {
      "limits": [
        {
          "counter": "create_database_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches PySqlitMCP, so you can run agents against it safely.

FAQ

Questions about create_database

What does the create_database tool do? +

create_database. It is categorised as a Write tool in the PySqlitMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_database? +

Register the PySqlit MCP server in PolicyLayer and add a rule for create_database: 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 PySqlitMCP. Nothing to install.

What risk level is create_database? +

create_database is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_database? +

Yes. Add a rate_limit block to the create_database 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.

How do I block create_database completely? +

Set action: deny in the PolicyLayer policy for create_database. 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.

What MCP server provides create_database? +

create_database is provided by the PySqlit MCP server (python51888/pysqlitmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.