manage_charts

SERVERMcp Google Sheets SOURCE@a1-x-tech/mcp-google-sheets

Medium RISK CLASS

Category Write

Parameters 122 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/a1-x-tech-mcp-google-sheets/manage-charts.md

WHAT IT DOES

What manage_charts does on Mcp Google Sheets

AI agents use manage_charts to create or update resources in Mcp Google Sheets, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Google Sheets environment.

Parameter	Type	Required	Description
`spec`	object	—	Raw Sheets API ChartSpec — full control; overrides the simplified fields above.
`title`	string	—	Chart title.
`action`	string	Yes	What to do with the charts.
`anchor`	object	—	add: place the chart over the grid, top-left at this cell.
`chart_id`	integer	—	update/delete: the chartId from get_spreadsheet or the add reply.
`new_sheet`	boolean	—	add: put the chart on its own new chart sheet instead.
`chart_type`	string	—	add/update: the chart kind (required unless spec is given).
`domain_range`	object	—	The x-axis (or pie label) values, incl. header cell.
`header_count`	integer	—	How many leading rows of the ranges are headers (default 1).
`series_ranges`	array	—	One range per data series, incl. header cells (PIE: exactly one).
`spreadsheet_id`	string	Yes	The spreadsheet id — the long id from the URL (docs.google.com/spreadsheets/d/<spreadsheetId>/edit) or from create_spreadsheet / search_spreadsheets output.
`legend_position`	string	—	BOTTOM_LEGEND, LEFT_LEGEND, RIGHT_LEGEND, TOP_LEGEND or NO_LEGEND (default: API's choice).

Parameters from the server's own tool schema.

RISK

Why manage_charts is rated Medium

Creates and modifies chart objects in spreadsheets, reversibly. No data deletion or financial operations.

From the tool's definition Manages embedded charts. action=add builds a chart from chart_type, places it with anchor or new_sheet

Risk signalsHigh parameter count (25 properties)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs manage_charts safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp Google Sheets, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For manage_charts, this is the rule to start with:

manage_charts Rate-limited

manage_charts stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "manage_charts": {
      "limits": [
        {
          "counter": "manage_charts_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Mcp Google Sheets, apply this rule, and every manage_charts call is checked against it from then on.

FAQ

Questions about manage_charts

What does the manage_charts tool do? +

Manages embedded charts. action=add builds a chart from chart_type (COLUMN/BAR/LINE/AREA/STEPPED_AREA/SCATTER/PIE), domain_range (x-axis labels / pie labels), series_ranges (one grid range per data series; PIE takes exactly one) and optional title/legend_position/header_count (rows of the ranges treated as headers, default 1) — place it with anchor {sheet_id,row_index,column_index} (the cell under the chart's top-left corner) or new_sheet=true for its own chart sheet; the reply carries the new chartId. Ranges should be single columns (or rows) including the header cell. For chart kinds beyond the basic set (combo, waterfall, histogram, org …) pass a raw Sheets API ChartSpec via spec instead — it overrides the simplified fields. action=update REPLACES the whole spec of an existing chart (chart_id + the same spec-building fields; there is no partial chart update). action=delete removes the chart by chart_id. Find chartIds via get_spreadsheet (sheets[].charts). It is categorised as a Write tool in the Mcp Google Sheets MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does manage_charts accept? +

manage_charts accepts 12 parameters: spec, title, action, anchor, chart_id, new_sheet, chart_type, domain_range, header_count, series_ranges, spreadsheet_id, legend_position. Required: action, spreadsheet_id. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on manage_charts? +

Register the Mcp Google Sheets MCP server in PolicyLayer and add a rule for manage_charts: 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 Google Sheets. Nothing to install.

What risk level is manage_charts? +

manage_charts is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit manage_charts? +

Yes. Add a rate_limit block to the manage_charts 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 manage_charts completely? +

Set action: deny in the PolicyLayer policy for manage_charts. 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 manage_charts? +

manage_charts is provided by the Mcp Google Sheets MCP server (@a1-x-tech/mcp-google-sheets). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Mcp Google Sheets, and thousands of servers like it.

This server

All 20 Mcp Google Sheets tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →