Skip to main content
Glama
arinspunk

Claude Talk to Figma MCP

by arinspunk

set_grid

Apply layout grids to Figma frames by specifying grid pattern, count, size, gutter, offset, alignment, visibility, and color for columns, rows, or custom grids.

Instructions

Apply layout grids to a frame node in Figma. Supports columns, rows, and grid patterns.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nodeIdYesThe ID of the frame node to apply grids to
gridsYesArray of layout grids to apply

Implementation Reference

  • Registration of the 'set_grid' MCP tool using server.tool() with the name 'set_grid'. Defines schema for nodeId and grids parameters.
    // Set Layout Grid Tool
    server.tool(
      "set_grid",
      "Apply layout grids to a frame node in Figma. Supports columns, rows, and grid patterns.",
      {
        nodeId: z.string().describe("The ID of the frame node to apply grids to"),
        grids: coerceJson(z.array(
          z.object({
            pattern: z.enum(["COLUMNS", "ROWS", "GRID"]).describe("Grid pattern type"),
            count: z.coerce.number().optional().describe("Number of columns/rows (ignored for GRID)"),
            sectionSize: z.coerce.number().optional().describe("Size of each section in pixels"),
            gutterSize: z.coerce.number().optional().describe("Gutter size between sections in pixels"),
            offset: z.coerce.number().optional().describe("Offset from the edge in pixels"),
            alignment: z.enum(["MIN", "CENTER", "MAX", "STRETCH"]).optional().describe("Grid alignment"),
            visible: z.boolean().optional().describe("Whether the grid is visible (default: true)"),
            color: z.object({
              r: z.coerce.number().min(0).max(1).describe("Red (0-1)"),
              g: z.coerce.number().min(0).max(1).describe("Green (0-1)"),
              b: z.coerce.number().min(0).max(1).describe("Blue (0-1)"),
              a: z.coerce.number().min(0).max(1).describe("Alpha (0-1)")
            }).optional().describe("Grid color")
          })
        )).describe("Array of layout grids to apply")
      },
      async ({ nodeId, grids }) => {
        try {
          const result = await sendCommandToFigma("set_grid", { nodeId, grids });
          const typedResult = result as { name: string; gridCount: number };
          return {
            content: [
              {
                type: "text",
                text: `Applied ${typedResult.gridCount} layout grid(s) to frame "${typedResult.name}"`,
              },
            ],
          };
        } catch (error) {
          return {
            content: [
              {
                type: "text",
                text: `Error setting layout grids: ${error instanceof Error ? error.message : String(error)}`,
              },
            ],
          };
        }
      }
    );
  • Handler function for 'set_grid'. Sends a 'set_grid' command to Figma via WebSocket with nodeId and grids, then returns the result indicating how many grids were applied.
    async ({ nodeId, grids }) => {
      try {
        const result = await sendCommandToFigma("set_grid", { nodeId, grids });
        const typedResult = result as { name: string; gridCount: number };
        return {
          content: [
            {
              type: "text",
              text: `Applied ${typedResult.gridCount} layout grid(s) to frame "${typedResult.name}"`,
            },
          ],
        };
      } catch (error) {
        return {
          content: [
            {
              type: "text",
              text: `Error setting layout grids: ${error instanceof Error ? error.message : String(error)}`,
            },
          ],
        };
      }
    }
  • Input schema for 'set_grid' tool: requires nodeId (string) and grids (array of objects with pattern, count, sectionSize, gutterSize, offset, alignment, visible, color fields).
    {
      nodeId: z.string().describe("The ID of the frame node to apply grids to"),
      grids: coerceJson(z.array(
        z.object({
          pattern: z.enum(["COLUMNS", "ROWS", "GRID"]).describe("Grid pattern type"),
          count: z.coerce.number().optional().describe("Number of columns/rows (ignored for GRID)"),
          sectionSize: z.coerce.number().optional().describe("Size of each section in pixels"),
          gutterSize: z.coerce.number().optional().describe("Gutter size between sections in pixels"),
          offset: z.coerce.number().optional().describe("Offset from the edge in pixels"),
          alignment: z.enum(["MIN", "CENTER", "MAX", "STRETCH"]).optional().describe("Grid alignment"),
          visible: z.boolean().optional().describe("Whether the grid is visible (default: true)"),
          color: z.object({
            r: z.coerce.number().min(0).max(1).describe("Red (0-1)"),
            g: z.coerce.number().min(0).max(1).describe("Green (0-1)"),
            b: z.coerce.number().min(0).max(1).describe("Blue (0-1)"),
            a: z.coerce.number().min(0).max(1).describe("Alpha (0-1)")
          }).optional().describe("Grid color")
        })
      )).describe("Array of layout grids to apply")
  • Type definition for FigmaCommand union type, includes 'set_grid' as a valid command string.
    | "set_grid"
  • sendCommandToFigma function that sends the 'set_grid' command (or any FigmaCommand) over WebSocket to the Figma plugin. Constructs the message with command name and params, tracks pending requests with timeout.
    export function sendCommandToFigma(
      command: FigmaCommand,
      params: unknown = {},
      timeoutMs: number = 300000
    ): Promise<unknown> {
      return new Promise((resolve, reject) => {
        // If not connected, try to connect first
        if (!ws || ws.readyState !== WebSocket.OPEN) {
          connectToFigma();
          reject(new Error("Not connected to Figma. Attempting to connect..."));
          return;
        }
    
        // Check if we need a channel for this command
        const requiresChannel = command !== "join";
        if (requiresChannel && !currentChannel) {
          reject(new Error("Must join a channel before sending commands"));
          return;
        }
    
        const id = uuidv4();
        const request = {
          id,
          type: command === "join" ? "join" : "message",
          ...(command === "join"
            ? { channel: (params as any).channel, sessionId: SESSION_ID }
            : { channel: currentChannel }),
          message: {
            id,
            command,
            params: {
              ...(params as any),
              commandId: id, // Include the command ID in params
            },
          },
        };
    
        // Set timeout for request
        const timeout = setTimeout(() => {
          if (pendingRequests.has(id)) {
            pendingRequests.delete(id);
            logger.error(`Request ${id} to Figma timed out after ${timeoutMs / 1000} seconds`);
            reject(new Error('Request to Figma timed out'));
          }
        }, timeoutMs);
    
        // Store the promise callbacks to resolve/reject later
        pendingRequests.set(id, {
          resolve,
          reject,
          timeout,
          lastActivity: Date.now()
        });
    
        // Send the request
        logger.info(`Sending command to Figma: ${command}`);
        logger.debug(`Request details: ${JSON.stringify(request)}`);
        ws.send(JSON.stringify(request));
      });
    }

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.8.2

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description must disclose behavioral traits. It implies mutation but does not state whether grids replace existing ones, if node must be a frame, or any side effects. Lacks crucial context for a destructive action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence efficiently conveys core purpose. Could be slightly more structured but no waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (nested object parameters, no output schema), the description is too minimal. Does not explain behavioral nuances like grid replacement, constraints on count vs sectionSize, or what 'apply' entails. Sibling tools like get_grid exist, but no cross-reference.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with all parameters described. The description adds 'columns, rows, grid patterns' which maps to the pattern enum, but does not provide additional meaning beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Apply' and the resource 'layout grids to a frame node'. It distinguishes from siblings like set_fill_color or get_grid by focusing on grid patterns, listing supported types (columns, rows, grid).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like set_fill_color or other 'set_*' tools. Does not specify prerequisites (e.g., node must be a frame) or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools