Read data from a Numbers spreadsheet. Optionally specify sheet, table, and cell range.
AI agents call numbers.read to retrieve information from Orchard without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves spreadsheet data without side effects. It allows querying specific sheets, tables, or cell ranges from Numbers documents, but performs no writes, deletions, or external operations. The blast radius of misuse is confined to potential exposure of sensitive spreadsheet contents, which is a read-access concern.
From the tool's definition Tool name is 'numbers.read' and description states it 'Read[s] data from a Numbers spreadsheet.' The verb 'read' and the explicit 'read data' phrasing indicate retrieval only. No modification, deletion, execution, or financial operations are described.
Documented attack patterns abuse exactly the kind of access numbers.read 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.read:
{
"version": "1",
"default": "deny",
"tools": {
"numbers.read": {}
}
}numbers.read is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Read data from a Numbers spreadsheet. Optionally specify sheet, table, and cell range. It is categorised as a Read tool in the Orchard MCP Server, which means it retrieves data without modifying state.
Register the Orchard MCP server in PolicyLayer and add a rule for numbers.read: 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.read is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the numbers.read 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.read. 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.read 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.