Read .xlsx or .csv. Returns header + rows (up to max_rows, hard cap 10_000).
AI agents call read_spreadsheet to retrieve information from Nexus Core without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from spreadsheet files without any side effects. It performs a query-like operation (listing rows up to a maximum) with no capability to modify, delete, or execute code. It is a straightforward data retrieval function with read-only semantics.
From the tool's definition Tool name is 'read_spreadsheet' and description states 'Read .xlsx or .csv. Returns header + rows'. The verb 'Read' and return-only behavior with no mention of modification, deletion, or execution.
Attacks that exploit this kind of access
Read .xlsx or .csv. Returns header + rows (up to max_rows, hard cap 10_000). It is categorised as a Read tool in the Nexus Core MCP Server, which means it retrieves data without modifying state.
Register the Nexus Core MCP server in PolicyLayer and add a rule for read_spreadsheet: 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 Nexus Core. Nothing to install.
read_spreadsheet 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 read_spreadsheet 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 read_spreadsheet. 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.
read_spreadsheet is provided by the Nexus Core MCP server (noumenon-ai/nexus-core). 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 →