Low Risk

group_by

Group data by columns and perform aggregation (like Excel Pivot Table). Returns grouped results with aggregated values. Supports multiple grouping columns for hierarchical analysis. Use for: pivot tables, data summarization, category analysis, hierarchical grouping, sales by region/product, perfo...

How to control group_by ↓

What group_by does on Mcp Excel

AI agents call group_by to retrieve information from Mcp Excel without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why group_by needs a policy

group_by is a pure read operation that retrieves, groups, and aggregates existing data without modifying, deleting, or executing arbitrary code. It performs the same function as Excel's Pivot Table feature—summarizing data through grouping and aggregation. There are no side effects, data modification, deletion, or financial implications.

From the tool's definition The tool description explicitly states it 'Group data by columns and perform aggregation' and returns 'grouped results with aggregated values'.

Documented attack patterns abuse exactly the kind of access group_by gives an agent:

How to control group_by

PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Excel, and nothing reaches the server without passing your rules. This is the rule we recommend for group_by:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "group_by": {}
  }
}

group_by is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Mcp Excel — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about group_by

What does the group_by tool do? +

Group data by columns and perform aggregation (like Excel Pivot Table). Returns grouped results with aggregated values. Supports multiple grouping columns for hierarchical analysis. Use for: pivot tables, data summarization, category analysis, hierarchical grouping, sales by region/product, performance by team/month. EXAMPLES: Revenue by product category, Average salary by department and job level, Count of orders by customer and month. It is categorised as a Read tool in the Mcp Excel MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on group_by? +

Register the Mcp Excel MCP server in PolicyLayer and add a rule for group_by: 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 Mcp Excel. Nothing to install.

What risk level is group_by? +

group_by is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit group_by? +

Yes. Add a rate_limit block to the group_by 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.

How do I block group_by completely? +

Set action: deny in the PolicyLayer policy for group_by. 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.

What MCP server provides group_by? +

group_by is provided by the Mcp Excel MCP server (jwadow/mcp-excel). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mcp Excel tool call.

Start from Mcp Excel, 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.

25 Mcp Excel tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.