Skip to main content
Glama
arinspunk

Claude Talk to Figma MCP

by arinspunk

set_variable

Create or update a variable in a Figma design system by specifying its name, type (color, float, string, boolean), and value. Optionally create a new variable collection if provided collection name doesn't exist.

Instructions

Create or update a variable in a Figma variable collection. Creates the collection if collectionName is provided and it doesn't exist.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
collectionIdNoID of an existing variable collection
collectionNameNoName for a new collection (used if collectionId not provided)
nameYesVariable name
resolvedTypeYesVariable type
valueNoVariable value. COLOR: {r,g,b,a} (0-1). FLOAT: number. STRING: string. BOOLEAN: boolean.
modeIdNoMode ID to set the value for (uses default mode if omitted)

Implementation Reference

  • The handler for the 'set_variable' tool. Registers the tool on the MCP server with Zod schema for inputs (collectionId, collectionName, name, resolvedType, value, modeId) and sends the command via WebSocket to Figma.
    // Set Variable Tool
    server.tool(
      "set_variable",
      "Create or update a variable in a Figma variable collection. Creates the collection if collectionName is provided and it doesn't exist.",
      {
        collectionId: z.string().optional().describe("ID of an existing variable collection"),
        collectionName: z.string().optional().describe("Name for a new collection (used if collectionId not provided)"),
        name: z.string().describe("Variable name"),
        resolvedType: z.enum(["COLOR", "FLOAT", "STRING", "BOOLEAN"]).describe("Variable type"),
        value: z.any().describe("Variable value. COLOR: {r,g,b,a} (0-1). FLOAT: number. STRING: string. BOOLEAN: boolean."),
        modeId: z.string().optional().describe("Mode ID to set the value for (uses default mode if omitted)"),
      },
      async ({ collectionId, collectionName, name, resolvedType, value, modeId }) => {
        try {
          const result = await sendCommandToFigma("set_variable", {
            collectionId,
            collectionName,
            name,
            resolvedType,
            value,
            modeId,
          });
          const typedResult = result as { variableId: string; variableName: string; collectionName: string };
          return {
            content: [
              {
                type: "text",
                text: `Set variable "${typedResult.variableName}" in collection "${typedResult.collectionName}" (ID: ${typedResult.variableId})`,
              },
            ],
          };
        } catch (error) {
          return {
            content: [
              {
                type: "text",
                text: `Error setting variable: ${error instanceof Error ? error.message : String(error)}`,
              },
            ],
          };
        }
      }
    );
  • Zod schema definition for the 'set_variable' tool inputs: collectionId (optional), collectionName (optional), name (required), resolvedType (enum: COLOR/FLOAT/STRING/BOOLEAN), value (any), modeId (optional).
    {
      collectionId: z.string().optional().describe("ID of an existing variable collection"),
      collectionName: z.string().optional().describe("Name for a new collection (used if collectionId not provided)"),
      name: z.string().describe("Variable name"),
      resolvedType: z.enum(["COLOR", "FLOAT", "STRING", "BOOLEAN"]).describe("Variable type"),
      value: z.any().describe("Variable value. COLOR: {r,g,b,a} (0-1). FLOAT: number. STRING: string. BOOLEAN: boolean."),
      modeId: z.string().optional().describe("Mode ID to set the value for (uses default mode if omitted)"),
  • Registration of the 'set_variable' tool via server.tool() inside registerVariableTools(server), which is called from registerTools(server) in server.ts.
    // Set Variable Tool
    server.tool(
      "set_variable",
      "Create or update a variable in a Figma variable collection. Creates the collection if collectionName is provided and it doesn't exist.",
      {
        collectionId: z.string().optional().describe("ID of an existing variable collection"),
        collectionName: z.string().optional().describe("Name for a new collection (used if collectionId not provided)"),
        name: z.string().describe("Variable name"),
        resolvedType: z.enum(["COLOR", "FLOAT", "STRING", "BOOLEAN"]).describe("Variable type"),
        value: z.any().describe("Variable value. COLOR: {r,g,b,a} (0-1). FLOAT: number. STRING: string. BOOLEAN: boolean."),
        modeId: z.string().optional().describe("Mode ID to set the value for (uses default mode if omitted)"),
      },
      async ({ collectionId, collectionName, name, resolvedType, value, modeId }) => {
        try {
          const result = await sendCommandToFigma("set_variable", {
            collectionId,
            collectionName,
            name,
            resolvedType,
            value,
            modeId,
          });
          const typedResult = result as { variableId: string; variableName: string; collectionName: string };
          return {
            content: [
              {
                type: "text",
                text: `Set variable "${typedResult.variableName}" in collection "${typedResult.collectionName}" (ID: ${typedResult.variableId})`,
              },
            ],
          };
        } catch (error) {
          return {
            content: [
              {
                type: "text",
                text: `Error setting variable: ${error instanceof Error ? error.message : String(error)}`,
              },
            ],
          };
        }
      }
    );
  • Type definition: 'set_variable' is included as a valid value in the FigmaCommand union type, ensuring type safety for commands sent via WebSocket.
    | "set_variable"
  • The sendCommandToFigma helper function used by the set_variable handler to send the command string 'set_variable' via WebSocket to the Figma plugin server.
    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));
      });
    }
Behavior2/5

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

No annotations are provided, so the description carries full burden. It discloses the creation of collections as a side effect, but lacks details on mutation behavior (overwriting existing variables), authorization needs, or error conditions. For a write operation, more transparency is expected.

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

Conciseness5/5

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

The description is two sentences long, front-loaded with the main purpose, and every sentence adds necessary context. No redundant or filler content.

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?

Despite high parameter coverage, the description omits information about the return value (e.g., what is output after creation/update) and error cases. For a tool with 6 parameters and no output schema, this is a significant gap.

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

Parameters4/5

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

Schema coverage is 100% and descriptions are included, but the description adds value beyond schema by explaining the conditional creation of collections based on collectionName. The value parameter also includes example formats (e.g., COLOR: {r,g,b,a}). This exceeds baseline 3.

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 'Create or update' and the specific resource 'a variable in a Figma variable collection'. It also adds the side effect of creating the collection if needed, which distinguishes it from sibling tools like get_variables or switch_variable_mode.

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

Usage Guidelines3/5

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

The description implies usage for creating or updating variables, but does not explicitly state when to use this tool versus alternatives (e.g., other variable tools). No exclusions or prerequisites are mentioned, leaving the agent with implicit guidance.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/arinspunk/claude-talk-to-figma-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server