board_place
Reparent an existing node (a card or piece instance) onto a board cell by id and snap it to the cell anchor. Undoable node authoring. The target cell is <board>/cell_<cell>; align offsets the node from the cell origin (default centred). Returns the node's new path.
This record as markdown: /tools/breakpoint-mcp/board-place.md
What board_place does on Breakpoint
AI agents use board_place 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 |
|---|---|---|---|
cell | string | Yes | Cell id to place onto (resolves to <board>/cell_<cell>) |
node | string | Yes | Node path of the node to place (a card / piece already in the scene) |
align | object | — | Offset from the cell origin in px (default 0,0 — centred on the anchor) |
board | string | Yes | Board root node path in the open scene ("." if the board is the scene root) |
Parameters from the server's own tool schema.
Why board_place is rated Medium
This tool modifies the hierarchical structure and position of nodes within a board system by reparenting them to new cell locations. While the changes are reversible (undoable), they represent persistent modifications to the authoring state. This falls under Write rather than Execute because it manipulates data structures deterministically rather than triggering arbitrary external operations.
From the tool's definition Tool description states 'Reparent an existing node' and 'snap it to the cell anchor', indicating modification of existing data structure. Explicitly marked as 'Undoable node authoring', confirming reversibility.
Attacks that exploit this kind of access
The rule that runs board_place 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 board_place, this is the rule to start with:
board_place 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 board_place call is checked against it from then on.
Questions about board_place
Reparent an existing node (a card or piece instance) onto a board cell by id and snap it to the cell anchor. Undoable node authoring. The target cell is <board>/cell_<cell>; align offsets the node from the cell origin (default centred). Returns the node's new path. 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.
board_place accepts 4 parameters: cell, node, align, board. Required: cell, node, board. 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 board_place: 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.
board_place 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 board_place 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 board_place. 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.
board_place 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