Read a sheet and return its contents as JSON records.
AI agents call excel_read_range to retrieve information from ExcelReadMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries data from Excel sheets without any side effects, modifications, or external operations. It matches the 'Read' category definition precisely: it queries data (sheet contents) and returns results without changing the underlying data or triggering further actions.
From the tool's definition Tool name 'excel_read_range' and description 'Read a sheet and return its contents as JSON records' explicitly indicate data retrieval with no modification.
Attacks that exploit this kind of access
Read a sheet and return its contents as JSON records. It is categorised as a Read tool in the ExcelReadMCP MCP Server, which means it retrieves data without modifying state.
Register the ExcelRead MCP server in PolicyLayer and add a rule for excel_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 ExcelReadMCP. Nothing to install.
excel_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 excel_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 excel_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.
excel_read_range is provided by the ExcelRead MCP server (ogumarusuisan/excelreadmcp). 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 →