Skip to main content
Glama
paragdesai1

Cursor Talk to Figma MCP

by paragdesai1

create_text

Add text elements to Figma designs by specifying position, content, and styling properties like font size, weight, and color.

Instructions

Create a new text element in Figma

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
xYesX position
yYesY position
textYesText content
fontSizeNoFont size (default: 14)
fontWeightNoFont weight (e.g., 400 for Regular, 700 for Bold)
fontColorNoFont color in RGBA format
nameNoSemantic layer name for the text node
parentIdNoOptional parent node ID to append the text to

Implementation Reference

  • The core handler function that creates a Figma text node, loads Inter font based on weight, sets text content using setCharacters helper, applies color fill, positions it, and appends to specified parent or current page. Returns detailed node info.
    async function createText(params) {
      const {
        x = 0,
        y = 0,
        text = "Text",
        fontSize = 14,
        fontWeight = 400,
        fontColor = { r: 0, g: 0, b: 0, a: 1 }, // Default to black
        name = "",
        parentId,
      } = params || {};
    
      // Map common font weights to Figma font styles
      const getFontStyle = (weight) => {
        switch (weight) {
          case 100:
            return "Thin";
          case 200:
            return "Extra Light";
          case 300:
            return "Light";
          case 400:
            return "Regular";
          case 500:
            return "Medium";
          case 600:
            return "Semi Bold";
          case 700:
            return "Bold";
          case 800:
            return "Extra Bold";
          case 900:
            return "Black";
          default:
            return "Regular";
        }
      };
    
      const textNode = figma.createText();
      textNode.x = x;
      textNode.y = y;
      textNode.name = name || text;
      try {
        await figma.loadFontAsync({
          family: "Inter",
          style: getFontStyle(fontWeight),
        });
        textNode.fontName = { family: "Inter", style: getFontStyle(fontWeight) };
        textNode.fontSize = parseInt(fontSize);
      } catch (error) {
        console.error("Error setting font size", error);
      }
      setCharacters(textNode, text);
    
      // Set text color
      const paintStyle = {
        type: "SOLID",
        color: {
          r: parseFloat(fontColor.r) || 0,
          g: parseFloat(fontColor.g) || 0,
          b: parseFloat(fontColor.b) || 0,
        },
        opacity: parseFloat(fontColor.a) || 1,
      };
      textNode.fills = [paintStyle];
    
      // If parentId is provided, append to that node, otherwise append to current page
      if (parentId) {
        const parentNode = await figma.getNodeByIdAsync(parentId);
        if (!parentNode) {
          throw new Error(`Parent node not found with ID: ${parentId}`);
        }
        if (!("appendChild" in parentNode)) {
          throw new Error(`Parent node does not support children: ${parentId}`);
        }
        parentNode.appendChild(textNode);
      } else {
        figma.currentPage.appendChild(textNode);
      }
    
      return {
        id: textNode.id,
        name: textNode.name,
        x: textNode.x,
        y: textNode.y,
        width: textNode.width,
        height: textNode.height,
        characters: textNode.characters,
        fontSize: textNode.fontSize,
        fontWeight: fontWeight,
        fontColor: fontColor,
        fontName: textNode.fontName,
        fills: textNode.fills,
        parentId: textNode.parent ? textNode.parent.id : undefined,
      };
    }
  • MCP tool registration for 'create_text'. Defines input schema with zod validation for parameters like position, text, font properties, and proxies the command to the Figma plugin via WebSocket, returning success message with created node ID.
    server.tool(
      "create_text",
      "Create a new text element in Figma",
      {
        x: z.number().describe("X position"),
        y: z.number().describe("Y position"),
        text: z.string().describe("Text content"),
        fontSize: z.number().optional().describe("Font size (default: 14)"),
        fontWeight: z
          .number()
          .optional()
          .describe("Font weight (e.g., 400 for Regular, 700 for Bold)"),
        fontColor: z
          .object({
            r: z.number().min(0).max(1).describe("Red component (0-1)"),
            g: z.number().min(0).max(1).describe("Green component (0-1)"),
            b: z.number().min(0).max(1).describe("Blue component (0-1)"),
            a: z
              .number()
              .min(0)
              .max(1)
              .optional()
              .describe("Alpha component (0-1)"),
          })
          .optional()
          .describe("Font color in RGBA format"),
        name: z
          .string()
          .optional()
          .describe("Semantic layer name for the text node"),
        parentId: z
          .string()
          .optional()
          .describe("Optional parent node ID to append the text to"),
      },
      async ({ x, y, text, fontSize, fontWeight, fontColor, name, parentId }) => {
        try {
          const result = await sendCommandToFigma("create_text", {
            x,
            y,
            text,
            fontSize: fontSize || 14,
            fontWeight: fontWeight || 400,
            fontColor: fontColor || { r: 0, g: 0, b: 0, a: 1 },
            name: name || "Text",
            parentId,
          });
          const typedResult = result as { name: string; id: string };
          return {
            content: [
              {
                type: "text",
                text: `Created text "${typedResult.name}" with ID: ${typedResult.id}`,
              },
            ],
          };
        } catch (error) {
          return {
            content: [
              {
                type: "text",
                text: `Error creating text: ${error instanceof Error ? error.message : String(error)
                  }`,
              },
            ],
          };
        }
      }
    );
  • Zod schema defining input parameters for the create_text tool: position (x,y), text content, optional fontSize, fontWeight, fontColor (RGBA), name, and parentId.
    {
      x: z.number().describe("X position"),
      y: z.number().describe("Y position"),
      text: z.string().describe("Text content"),
      fontSize: z.number().optional().describe("Font size (default: 14)"),
      fontWeight: z
        .number()
        .optional()
        .describe("Font weight (e.g., 400 for Regular, 700 for Bold)"),
      fontColor: z
        .object({
          r: z.number().min(0).max(1).describe("Red component (0-1)"),
          g: z.number().min(0).max(1).describe("Green component (0-1)"),
          b: z.number().min(0).max(1).describe("Blue component (0-1)"),
          a: z
            .number()
            .min(0)
            .max(1)
            .optional()
            .describe("Alpha component (0-1)"),
        })
        .optional()
        .describe("Font color in RGBA format"),
      name: z
        .string()
        .optional()
        .describe("Semantic layer name for the text node"),
      parentId: z
        .string()
        .optional()
        .describe("Optional parent node ID to append the text to"),
    },
  • Dispatch case in handleCommand switch statement that routes 'create_text' commands to the createText handler function.
          return await createText(params);
        case "set_fill_color":
          return await setFillColor(params);
        case "set_stroke_color":
          return await setStrokeColor(params);
        case "move_node":
          return await moveNode(params);
        case "resize_node":
          return await resizeNode(params);
        case "delete_node":
          return await deleteNode(params);
        case "delete_multiple_nodes":
          return await deleteMultipleNodes(params);
        case "get_styles":
          return await getStyles();
        case "get_local_components":
          return await getLocalComponents();
        // case "get_team_components":
        //   return await getTeamComponents();
        case "create_component_instance":
          return await createComponentInstance(params);
        case "export_node_as_image":
          return await exportNodeAsImage(params);
        case "set_corner_radius":
          return await setCornerRadius(params);
        case "set_text_content":
          return await setTextContent(params);
        case "clone_node":
          return await cloneNode(params);
        case "scan_text_nodes":
          return await scanTextNodes(params);
        case "set_multiple_text_contents":
          return await setMultipleTextContents(params);
        case "get_annotations":
          return await getAnnotations(params);
        case "set_annotation":
          return await setAnnotation(params);
        case "scan_nodes_by_types":
          return await scanNodesByTypes(params);
        case "set_multiple_annotations":
          return await setMultipleAnnotations(params);
        case "set_layout_mode":
          return await setLayoutMode(params);
        case "set_padding":
          return await setPadding(params);
        case "set_axis_align":
          return await setAxisAlign(params);
        case "set_layout_sizing":
          return await setLayoutSizing(params);
        case "set_item_spacing":
          return await setItemSpacing(params);
        default:
          throw new Error(`Unknown command: ${command}`);
      }
    }

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv1.0.0
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / fontColor
      Added value: +{
      +  "description": "Font color in RGBA format",
      +  "properties": {
      +    "a": {
      +      "description": "Alpha component (0-1)",
      +      "maximum": 1,
      +      "minimum": 0,
      +      "type": "number"
      +    },
      +    "b": {
      +      "description": "Blue component (0-1)",
      +      "maximum": 1,
      +      "minimum": 0,
      +      "type": "number"
      +    },
      +    "g": {
      +      "description": "Green component (0-1)",
      +      "maximum": 1,
      +      "minimum": 0,
      +      "type": "number"
      +    },
      +    "r": {
      +      "description": "Red component (0-1)",
      +      "maximum": 1,
      +      "minimum": 0,
      +      "type": "number"
      +    }
      +  },
      +  "required": [
      +    "r",
      +    "g",
      +    "b"
      +  ],
      +  "type": "object"
      +}
    • addedInput schema / properties / fontSize
      Added value: +{
      +  "description": "Font size (default: 14)",
      +  "type": "number"
      +}
    • addedInput schema / properties / fontWeight
      Added value: +{
      +  "description": "Font weight (e.g., 400 for Regular, 700 for Bold)",
      +  "type": "number"
      +}
    • addedInput schema / properties / name
      Added value: +{
      +  "description": "Semantic layer name for the text node",
      +  "type": "string"
      +}
    • addedInput schema / properties / parentId
      Added value: +{
      +  "description": "Optional parent node ID to append the text to",
      +  "type": "string"
      +}
    • addedInput schema / properties / text
      Added value: +{
      +  "description": "Text content",
      +  "type": "string"
      +}
    • addedInput schema / properties / x
      Added value: +{
      +  "description": "X position",
      +  "type": "number"
      +}
    • addedInput schema / properties / y
      Added value: +{
      +  "description": "Y position",
      +  "type": "number"
      +}
    • addedInput schema / required
      Added value: +[
      +  "x",
      +  "y",
      +  "text"
      +]
  2. First observed

TDQS

B3.2/5.0
Behavior2/5

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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It only states the basic action ('create') and reveals nothing about return values, side effects, permissions, or how it interacts with the document. This is a minimal but non-misleading disclosure.

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 a single, short, grammatically complete sentence with zero filler. It efficiently communicates the tool's purpose without unnecessary detail, matching the standard for appropriate conciseness.

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?

The tool has 8 parameters including a nested fontColor object and no output schema, yet the description provides no context about return values, default behavior, parent requirements, or typical use scenarios. The single-sentence description is insufficient for an agent to fully understand the tool's behavior in complex workflows.

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 description coverage is 100%, so all 8 parameters (x, y, text, name, fontSize, parentId, fontColor, fontWeight) have individual descriptions. The tool description adds no additional parameter meaning, so the schema already provides the needed semantics. 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 states a specific verb ('Create') and resource ('text element') with clear scope ('in Figma'). It distinguishes from sibling tools like set_text_content (which modifies) and create_rectangle (which creates a different resource type).

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 is provided on when to use this tool versus alternatives. It doesn't mention that set_text_content should be used for modifying existing text, or any context about parent frames or prerequisites. The description simply states what it does without guiding selection.

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