Read a specific cell range (e.g.
AI agents call numbers_read_range to retrieve information from Iwork without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves cell data from a Numbers spreadsheet without modifying, deleting, or executing operations. It is purely a data retrieval operation, fitting the Read category definition. Low severity because reading spreadsheet data poses minimal risk even in misuse scenarios—no data is modified or lost, and no external operations are triggered.
From the tool's definition Tool name explicitly contains 'read' and description indicates it retrieves data from a specific cell range with no indication of modification or side effects.
Documented attack patterns abuse exactly the kind of access numbers_read_range gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Iwork, and nothing reaches the server without passing your rules. This is the rule we recommend for numbers_read_range:
{
"version": "1",
"default": "deny",
"tools": {
"numbers_read_range": {}
}
}numbers_read_range 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 a specific cell range (e.g. It is categorised as a Read tool in the Iwork MCP Server, which means it retrieves data without modifying state.
Register the Iwork MCP server in PolicyLayer and add a rule for numbers_read_range: 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 Iwork. Nothing to install.
numbers_read_range 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_range 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_range. 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_range is provided by the Iwork MCP server (reichenbach/iwork_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Iwork, 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.
114 Iwork tools catalogued and risk-classified — across an index of 43,000+ MCP servers.