createOrUpdate
AI agents use createOrUpdate to create or update resources in Cloudflare MCP Lab — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cloudflare MCP Lab environment.
The tool name explicitly states it can create or update data. Given the server manages employee data in a SQL database, this is a Write operation that modifies data but does not irreversibly delete it. Severity is medium because unauthorized modifications to employee records could cause business disruption and privacy concerns, though changes are theoretically reversible.
From the tool's definition Tool name 'createOrUpdate' directly indicates creation or modification of data. In context of a SQL database with employee data, this tool creates new records or modifies existing ones reversibly.
Attacks that exploit this kind of access
createOrUpdate. It is categorised as a Write tool in the Cloudflare MCP Lab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cloudflare MCP Lab MCP server in PolicyLayer and add a rule for createOrUpdate: 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 Cloudflare MCP Lab. Nothing to install.
createOrUpdate 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 createOrUpdate 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 createOrUpdate. 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.
createOrUpdate is provided by the Cloudflare MCP Lab MCP server (ross-jill-ws/cloudflare-mcp-lab). 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 →