card_deck_from_table
Read a CSV or JSON table and stamp one card per row, binding columns to slots via a column map. Undoable node authoring. column_map values are bare {column} references or composed templates like "{name} · {role}"; a filter selects rows and an optional layout arranges them. Table columns no slot r...
This record as markdown: /tools/breakpoint-mcp/card-deck-from-table.md
What card_deck_from_table does on Breakpoint
AI agents use card_deck_from_table to create or update resources in Breakpoint, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Breakpoint environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | integer | — | Cap the number of rows stamped |
filter | object | — | Optional row selector, e.g. {column:'set', equals:'base'} |
format | string | — | Override the table format |
layout | object | — | Optional arrangement (same knobs as card_hand_layout); omitted → stacked at origin |
parent | string | Yes | Container node path the cards are instanced under; "." for the root |
face_up | boolean | — | Show the face (default true) |
persist | boolean | — | Bake each stamped card's bound slot data into the saved scene by enabling Editable Children on every card (default false = runtime-bound only, reverts on reload |
art_column | string | — | Column holding a res:// texture path bound to the `art` slot |
column_map | object | Yes | Slot name → column expression (a bare {column} or a composed "{a} · {b}") |
table_path | string | Yes | CSV or JSON table on disk (res:// or absolute); format auto-detected by extension unless `format` set |
template_path | string | Yes | Card template scene, e.g. res://ui/cards/Card.tscn |
Parameters from the server's own tool schema.
Why card_deck_from_table is rated Medium
The tool reads a CSV/JSON table and creates (stamps) card nodes from it — this is a Write operation (node authoring/creation). It is explicitly described as 'Undoable', ruling out Destructive. The read of the table is incidental to the primary action of creating new nodes.
From the tool's definition stamp one card per row, binding columns to slots via a column map. Undoable node authoring
Risk signalsHigh parameter count (22 properties)
Attacks that exploit this kind of access
The rule that runs card_deck_from_table safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Breakpoint, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For card_deck_from_table, this is the rule to start with:
card_deck_from_table 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 Breakpoint, apply this rule, and every card_deck_from_table call is checked against it from then on.
Questions about card_deck_from_table
Read a CSV or JSON table and stamp one card per row, binding columns to slots via a column map. Undoable node authoring. column_map values are bare {column} references or composed templates like "{name} · {role}"; a filter selects rows and an optional layout arranges them. Table columns no slot referenced are surfaced (not silently dropped). It is categorised as a Write tool in the Breakpoint MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
card_deck_from_table accepts 11 parameters: limit, filter, format, layout, parent, face_up, persist, art_column, column_map, table_path, template_path. Required: parent, column_map, table_path, template_path. The full parameter table on this page comes from the server's own tool schema.
Register the Breakpoint MCP server in PolicyLayer and add a rule for card_deck_from_table: 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 Breakpoint. Nothing to install.
card_deck_from_table 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 card_deck_from_table 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 card_deck_from_table. 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.
card_deck_from_table is provided by the Breakpoint MCP server (breakpoint-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Breakpoint, and thousands of servers like it.
This server
Across the catalogue