Create a new Numbers spreadsheet. Optionally provide initial data or a template.
AI agents use numbers.create to create or update resources in Orchard — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Orchard environment.
This tool creates new data (a Numbers spreadsheet) which is a Write operation. It is reversible (the created file can be deleted), so it does not qualify as Destructive. The severity is medium because uncontrolled creation could fill storage or clutter the user's file system, but the impact is bounded and recoverable. High confidence due to explicit 'Create' language and clear intent.
From the tool's definition Tool name 'numbers.create' and description 'Create a new Numbers spreadsheet' directly indicate creation of a new file/document with reversible effects.
Documented attack patterns abuse exactly the kind of access numbers.create gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Orchard, and nothing reaches the server without passing your rules. This is the rule we recommend for numbers.create:
{
"version": "1",
"default": "deny",
"tools": {
"numbers.create": {
"limits": [
{
"counter": "numbers.create_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}numbers.create 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.
Free to start. No card required.
Create a new Numbers spreadsheet. Optionally provide initial data or a template. It is categorised as a Write tool in the Orchard MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Orchard MCP server in PolicyLayer and add a rule for numbers.create: 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 Orchard. Nothing to install.
numbers.create 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 numbers.create 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 numbers.create. 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.
numbers.create is provided by the Orchard MCP server (l22-io/orchard-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Orchard, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
65 Orchard tools catalogued and risk-classified — across an index of 43,000+ MCP servers.