update_chart
Change a chart: its name, its type (pie, doughnut, line, area, bar, column, scatter) or the title of its vertical axis. Pass only what changes. add_data_sources adds series and remove_data_source_ids removes series by the ids list_charts shows (798); every other series stays as it is. To change o...
This record as markdown: /tools/com-quintadb-mcp/update-chart.md
What update_chart does on QuintaDB
AI agents use update_chart to create or update resources in QuintaDB, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your QuintaDB environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
app_id | string | Yes | Project ID (from list_projects) |
chart_id | string | Yes | |
new_name | string | — | |
type_code | string | — | pie, doughnut, line, area, bar, column, scatter |
y_axis_title | string | — | |
add_data_sources | array | — | Series to ADD to the ones the chart has |
remove_data_source_ids | array | — | Ids of the series to remove, from list_charts |
Parameters from the server's own tool schema.
Why update_chart is rated Medium
An AI agent can call update_chart faster than any human can review: one bad instruction and it creates or modifies resources in QuintaDB by the hundred, each call as confident as the last.
Risk signalsHigh parameter count (12 properties) · Bulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs update_chart safely
PolicyLayer is an MCP gateway: it sits between your AI agents and QuintaDB, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For update_chart, this is the rule to start with:
update_chart 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.
The button opens the PolicyLayer dashboard: create your workspace, connect QuintaDB, apply this rule, and every update_chart call is checked against it from then on.
Questions about update_chart
Change a chart: its name, its type (pie, doughnut, line, area, bar, column, scatter) or the title of its vertical axis. Pass only what changes. add_data_sources adds series and remove_data_source_ids removes series by the ids list_charts shows (798); every other series stays as it is. To change one series: remove it and add the new one in the same call. It does NOT change the horizontal axis (what the values are grouped by): for that create the chart you want with create_chart, then remove this one with delete_chart. Ids come from list_charts. It is categorised as a Write tool in the QuintaDB MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
update_chart accepts 7 parameters: app_id, chart_id, new_name, type_code, y_axis_title, add_data_sources, remove_data_source_ids. Required: app_id, chart_id. The full parameter table on this page comes from the server's own tool schema.
Register the QuintaDB MCP server in PolicyLayer and add a rule for update_chart: 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 QuintaDB. Nothing to install.
update_chart is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_chart 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 update_chart. 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.
update_chart is provided by the QuintaDB MCP server (https://quintadb.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on QuintaDB, and thousands of servers like it.
This server
Across the catalogue