AI agents call sheets_read to retrieve information from Access 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 a Google Sheets spreadsheet without creating, modifying, deleting, or executing operations. It is a read-only query operation with no side effects. Severity is low because unauthorized reading of spreadsheet data, while potentially sensitive, has minimal blast radius compared to write, execute, or destructive operations.
From the tool's definition Tool description explicitly states 'Read cell values' and 'Returns a 2D array of values. Use this to inspect data, headers, or specific ranges'. The verb 'read' and 'inspect' indicate retrieval without modification.
Attacks that exploit this kind of access
Read cell values from a Google Sheets spreadsheet using A1 notation. Returns a 2D array of values. Use this to inspect data, headers, or specific ranges before appending. It is categorised as a Read tool in the Access MCP Server, which means it retrieves data without modifying state.
Register the Access MCP server in PolicyLayer and add a rule for sheets_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 Access. Nothing to install.
sheets_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 sheets_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 sheets_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.
sheets_read is provided by the Access MCP server (scottpedia0/access). 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 →