Conduit
Enables comprehensive design operations in Figma including text manipulation, color and gradient management, AutoLayout creation, component and variant management, vector and image handling, layer operations, boolean operations, design token management, and real-time collaboration through event subscription.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Conduit create a blue rectangle with rounded corners in the center of the current page"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Conduit
Design at the speed of thought
https://github.com/user-attachments/assets/27fb8080-a4f6-46d4-a016-60ba3f0208e8
What is MCP?
Model Context Protocol (MCP) is the framework that allows an AI agent to communicate with external applications. This implementation enables any AI agent to send commands to and receive information from Figma in real-time.
How it works
+------------+ +-----+ +------------------------+ +--------------+
| AI Agent | <-> | MCP | <-> | Local WebSocket Server | <-> | Figma Plugin |
+------------+ +-----+ +------------------------+ +--------------+
Related MCP server: Figma MCP Server
Table of Contents
Features:
βοΈ Text manipulation β Add, edit, and style text elements, including advanced controls for font, size, weight, case, decoration, spacing, and paragraph/line height.
π¨ Gradient & color support β Create and apply solid colors, gradients, and color variables (design tokens) to any element.
π€ Font support β Access and apply a diverse range of fonts, including bulk font operations.
π AutoLayout β Automatically create responsive and adaptive layouts, including hug/fill sizing and all Figma auto-layout properties.
βοΈ Batch operations β Perform actions on multiple Figma elements simultaneously for efficient workflows.
π· Geometric shapes β Generate rectangles, circles, ellipses, polygons, lines, and star shapes.
π Vector & SVG support β Create, insert, and manipulate vector shapes and SVG graphics.
πΌοΈ Image support β Import, export, and manage raster images within Figma designs.
ποΈ Frame, Group, Component β Structure designs with frames, groups, reusable components, and component instances.
π§© Component variants & properties β Create, manage, and organize component variants and their properties.
π·οΈ Rename layers β Programmatically rename layers, including AI-powered renaming.
π Page management β Create, duplicate, and set the current page in your Figma document.
π Node management β Clone, delete, lock/unlock, show/hide, insert, flatten, reorder, move, and resize nodes.
βοΈ Boolean operations β Union, subtract, intersect, and exclude shapes for complex vector editing.
π Grids, guides, and constraints β Create and manage layout grids, guides, and responsive constraints.
β¨ Effect styles β Create, set, and apply effect styles (drop shadow, blur, etc.).
𧬠Figma Variables (Design Tokens) β Create, update, delete, and apply variables for color, number, string, and boolean; switch between variable modes (e.g., light/dark theme).
πΎ Export & code generation β Export nodes as images (PNG, JPG, SVG, PDF), generate HTML structure, and extract CSS from Figma nodes.
π Annotation support β Get, set, update, and delete annotations on nodes.
π Event subscription β Subscribe and unsubscribe to Figma events (e.g., selection change, document change). This essentially allows turn-by-turn multi-agent collaboration.
Compatibility
VSCode w/ GitHub Copilot agent (Sonnet 4.0) (50 free Sonnet 3.5 requests per month)
VSCode w/ Cline (Multiple LLM's available, Gemini has $300 free credits)
Claude Desktop Application (Sonnet 4.0)
Cursor agent (Sonnet 4.0 / GPT 4.1 / Gemini 2.5 pro)
Prerequisites
macOS/Linux:
curl -fsSL https://bun.sh/install | bashWindows:
irm bun.sh/install.ps1 | iexInstallation
Step 1: Install the server and plugin
Clone this repository:
git clone https://github.com/eonist/conduit.gitTerminal:
cd path-to-conduitTerminal:
npm install-> Builds dependenciesTerminal:
bun run build:all-> Builds the Server and PluginTerminal:
bun socket-> Starts the Server
Step 2: Install the Figma Plugin
Open Figma Desktop App
Go to
Plugins > Development > Import plugin from manifest...Navigate to conduit folder and select
conduit/src/plugin/manifest.jsonStart Figma plugin: Plugin -> Development -> Conduit
Step 3: Configure Agent
Open Agent App (GitHub Copilot Agent, Cline, Cursor, Claude desktop)
Find MCP settings in your agent app of choice.
~/.app-name/mcp.jsonAdd a new MCP connection with this config:
{
"mcpServers": {
"ConduitMCPServer": {
"command": "bunx",
"args": ["conduit-design@latest"]
}
}
}AI Agent app: Ensure MCP βConduitβ is enabled.
AI Agent app: "Talk to Figma on channel: (unique channel id copied from plugin)"
Quick Example
User: Talk to figma on channel "xxxxxxx"
Agent: Connecting to Figma. Connected on channel "xxxxxxxx"
User: "Create a responsive navigation bar with our brand color #3366FF and add 5 menu items"
Agent: [executes commands in Figma and displays the results]Docs:
Troubleshooting
Connection Error: Ensure the WebSocket server is running (
bun socket).Plugin Not Appearing: Verify the plugin import in Figma Development settings.
Execution or Font Loading Errors: Check Figmaβs development console for details.
In VSCode command pallet:> Reload Window this restarts cline and refreshes your MCP servers (To get new updates)
Testing
To run integration tests:
bun run testSee TESTING.md for more details.
There is also Unit-tests in the/tests/ path
Contributions
Fork the repository.
Create a branch (e.g.,
feature/amazing-feature).Commit your changes.
Push to your branch.
Open a Pull Request.
See MCP protocol design best pratice: https://gist.github.com/eonist/eb8d5628aad07fc57ce339e518158c20
License
MIT License β see the LICENSE file for details.
Authors
Sonny Lazuardi β Original implementation | GitHub
XΓΊlio ZΓ© β Adaptation for Claude | GitHub
AndrΓ© J β Adoption for any agent with new features | GitHub
Acknowledgments
Anthropic team for Claude and the Model Context Protocol.
Figma community for their excellent plugin API.
Sonny Lazuardi for the original implementation.
Bun team for providing a fast JavaScript runtime.
Available Tools
72 toolsapply_effect_styleBIdempotent
Applies an effect style to a node in Figma.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the updated node's ID.
Inputs: effectStyleId (required), nodeId (required).
booleanB
Perform boolean operations (union, subtract, intersect, exclude) on Figma nodes.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the result.
Inputs: no named parameters.
create_buttonAIdempotent
Creates a complete button with background and text in Figma at the specified coordinates. You can customize size, text, colors, font, corner radius, name, and parent node.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the created button's frame, background, and text node IDs.
Inputs: background, buttons, cornerRadius, fontSize, +9 more.
create_component_instanceA
Creates one or more component instances in Figma. Accepts either a single entry (via 'entry') or an array of entries (via 'entries').
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the created instance IDs.
Inputs: entries, entry.
create_components_from_nodeAIdempotent
Converts one or more existing nodes into components in Figma.
Returns:
content: Array of objects. Each object contains:
type: "text"
text: JSON string with created component IDs and any errors.
Inputs: entries, entry, skip_errors.
create_ellipseAIdempotent
Creates one or more ellipse nodes in the specified Figma document. Accepts either a single ellipse config (via 'ellipse') or an array of configs (via 'ellipses'). Optionally, you can provide a name, a parent node ID, fill color, stroke color, and stroke weight.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the created ellipse node ID(s).
Inputs: ellipse, ellipses.
create_frameAIdempotent
Creates one or more frame nodes in the specified Figma document. Accepts either a single frame config (via 'frame') or an array of configs (via 'frames'). Optionally, you can provide a name, a parent node ID, fill color, stroke color, stroke weight, and corner radius.
Corner radius can be:
A single number for uniform corners (e.g., 8)
An array of 4 numbers for individual corners [topLeft, topRight, bottomRight, bottomLeft] (e.g., [8, 8, 0, 0])
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the created frame node ID(s).
Inputs: frame, frames.
create_gradient_styleAIdempotent
Creates one or more gradient style variables in Figma.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the created gradient(s) ID(s) or a summary.
Inputs: gradients (required).
create_lineAIdempotent
Creates one or more line nodes in the specified Figma document. Accepts either a single line config (via 'line') or an array of configs (via 'lines'). Optionally, you can provide a parent node ID, stroke color, and stroke weight.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the created line node ID(s).
Inputs: line, lines.
create_polygonAIdempotent
Creates one or more polygons in Figma. Accepts either a single polygon config (via 'polygon') or an array of configs (via 'polygons'). Optionally, you can provide a name, a parent node ID, fill color, stroke color, and stroke weight.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the created polygon node ID(s).
Inputs: polygon, polygons.
create_rectangleAIdempotent
Creates one or more rectangle shape nodes in the specified Figma document. Accepts either a single rectangle config (via 'rectangle') or an array of configs (via 'rectangles'). Optionally, you can provide a name, a parent node ID to attach the rectangle(s) to, and a corner radius for rounded corners.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the created rectangle node ID(s).
Inputs: rectangle, rectangles.
create_vectorB
Creates one or more vector nodes in Figma. Use 'vector' for single or 'vectors' for batch.
Inputs: vector, vectors.
delete_nodeC
Deletes one or more nodes in Figma.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the deleted node's ID(s).
Inputs: nodeId, nodeIds.
detach_instancesAIdempotent
Detaches one or more Figma component instances from their masters. Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the detached instance's ID or error info.
Inputs: instanceId, instanceIds, options.
duplicate_nodeB
Clones one or more nodes in Figma. Accepts either a single node config (via 'node') or an array of configs (via 'nodes'). Optionally, you can specify positions, offsets, and parent.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the new node ID(s).
Inputs: node, nodes.
duplicate_pageA
Duplicate a Figma page and all its children as a new page.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the new page info as JSON.
Inputs: pageId (required), newPageName.
export_node_as_imageAIdempotent
Exports a node as an image from Figma in the specified format and scale.
Returns:
content: Array of objects. Each object contains type: "image", data (image data), and mimeType (image mime type).
Inputs: nodeId (required), format, scale.
flatten_nodeA
Flatten one or more nodes in Figma, or the current selection, merging all child vector layers and shapes into a single vector layer.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the results for each node.
Inputs: nodeId, nodeIds, selection.
get_annotationARead-onlyIdempotent
Get annotation(s) for one or more Figma nodes.
Returns:
For single: { nodeId, annotations }
For batch: Array<{ nodeId, annotations }>
Inputs: nodeId, nodeIds.
get_componentsARead-onlyIdempotent
Get components from the current document, a team library, or remote team libraries.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the components info as JSON.
Inputs: source (required), after, page_size, team_id.
get_constraintC
Get constraints for one or more Figma nodes (optionally including children).
Returns: Array of constraint info for each node, including children if requested.
Inputs: includeChildren, nodeId, nodeIds.
get_css_asyncARead-onlyIdempotent
Get CSS properties from a node.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the CSS properties as JSON.
Inputs: format, nodeId.
get_doc_pagesARead-onlyIdempotent
Get information about all pages in the current Figma document.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the pages info as JSON.
Inputs: no named parameters.
get_doc_styleARead-onlyIdempotent
Get all styles from the current Figma document.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the styles info as JSON.
Inputs: no named parameters.
get_document_infoARead-onlyIdempotent
Get detailed information about the current Figma document.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the document info as JSON.
Inputs: no named parameters.
get_fill_and_strokeB
Gets fill and/or stroke color(s) and stroke weight for one or more nodes.
Inputs: nodeId, nodeIds.
get_gridB
Get all layout grids for one or more Figma nodes (FRAME, COMPONENT, INSTANCE).
Returns: For single: { nodeId, grids: [...] }, for batch: Array<{ nodeId, grids: [...] }>.
Inputs: nodeId, nodeIds.
get_guideB
Get all guides on the current Figma page.
Returns: Array of guides, each with { axis, offset }
Inputs: no named parameters.
get_htmlBRead-onlyIdempotent
Generates HTML structure from Figma nodes.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the generated HTML string.
Inputs: nodeId (required), cssMode, format.
get_imageD
Inputs: no named parameters.
get_node_infoARead-onlyIdempotent
Get detailed information about one or more nodes in Figma.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the node(s) info as JSON.
Inputs: nodeId, nodeIds.
get_node_styleARead-onlyIdempotent
Get all style properties (fills, strokes, effects, text styles, style IDs, etc.) for one or more nodes.
Returns:
Array of { nodeId, styles } objects, one per node.
Inputs: nodeId, nodeIds.
get_pageB
Get info for one, many, or all pages.
Returns: For single: { pageId, name, isActive }, for batch: Array<{ pageId, name, isActive }>.
Inputs: no named parameters.
get_selectionARead-onlyIdempotent
Get information about the current selection in Figma.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the selection info as JSON.
Inputs: no named parameters.
get_styled_text_segmentsARead-onlyIdempotent
Get text segments with specific styling in a text node.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the styled text segments as JSON.
Inputs: nodeId (required), property (required).
get_svg_vectorARead-onlyIdempotent
Get SVG markup for one or more vector nodes.
Returns:
Array of { nodeId, svg } objects, one per node.
Inputs: nodeId, nodeIds.
get_text_styleD
Inputs: nodeId, nodeIds.
get_variantC
Get info about variants/properties for one or more component sets.
Returns: For single: { componentSetId, variants: [...] }, for batch: Array<{ componentSetId, variants: [...] }>.
Inputs: componentSetId, componentSetIds.
get_vectorBRead-onlyIdempotent
Retrieves one or more vector nodes by ID(s). Accepts 'nodeId' or 'nodeIds'.
Inputs: nodeId, nodeIds.
group_nodeAIdempotent
Groups or ungroups nodes in Figma, depending on the 'group' flag.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the result.
Inputs: group (required), name, nodeId, nodeIds.
joinBIdempotent
Join a specific channel to communicate with Figma.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the join status message.
Inputs: channel (required).
load_font_asyncC
Load a font asynchronously in Figma.
Returns:
content: Array containing a text message with the loaded font. Example: { "content": [{ "type": "text", "text": "Font loaded: Roboto" }] }
Inputs: family (required), style.
move_nodeAIdempotent
Moves one or more nodes to a new position in Figma. Accepts either a single move config (via 'move') or an array of configs (via 'moves').
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the moved node ID(s) and new position(s).
Inputs: move, moves.
rename_layerAIdempotent
Renames one or more nodes in Figma. Accepts either a single rename config (via 'rename') or an array of configs (via 'renames').
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the original and new name(s).
Inputs: rename, renames.
reorder_nodeA
Reorders one or more nodes in their parents' children arrays. Accepts either a single reorder config (via 'reorder') or an array of configs (via 'reorders'). Optionally, you can provide options such as skip_errors.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the results and any errors.
Inputs: options, reorder, reorders.
resize_nodeBIdempotent
Resize a node in Figma.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the resized node's ID and new size.
Inputs: height (required), nodeId (required), width (required).
rotate_nodeBIdempotent
Rotate a node in Figma.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the rotated node's ID, angle, and pivot info.
Inputs: angle (required), nodeId (required), pivot, pivotPoint.
scan_text_nodesARead-onlyIdempotent
Scan all text nodes in the selected Figma node.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the scan status and results.
Inputs: nodeId (required).
set_annotationA
Set, update, or delete annotation(s) for one or more Figma nodes.
Returns:
For single: { nodeId, updated/deleted }
For batch: Array<{ nodeId, updated/deleted }>
Inputs: entries, entry.
set_auto_layoutAIdempotent
Set, update, or delete one or more layout grids on Figma nodes (FRAME, COMPONENT, INSTANCE).
Returns: Array of result objects for each operation.
Inputs: layout.
set_auto_layout_resizingBIdempotent
Sets hug or fill sizing mode on an auto layout frame or child node in Figma.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the updated node's ID.
Inputs: axis (required), mode (required), nodeId (required).
set_constraintB
Set constraints (left/right/top/bottom/center/scale/stretch) for one or more Figma nodes.
Returns: Array of result objects for each operation.
Inputs: applyToChildren, constraint, constraints, maintainAspectRatio.
set_corner_radiusAIdempotent
Sets the corner radius of a node in Figma.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the updated node's ID.
Inputs: radius (required), corners.
set_effectAIdempotent
Set effect(s) directly or by style variable on one or more nodes in Figma.
Returns:
content: Array containing a text message with the updated node(s) ID(s) or a summary.
Inputs: entries (required).
set_fill_and_strokeC
Sets fill and/or stroke color(s) and/or stroke weight for one or more nodes.
Inputs: fill, fillColor, nodeId, nodeIds, +3 more.
set_gradientAIdempotent
Set a gradient on one or more nodes in Figma, either directly or by style variable.
Returns:
content: Array containing a text message with the updated node(s) ID(s) or a summary.
Inputs: entries (required).
set_gridC
Create, update, or delete one or more layout grids on Figma nodes (FRAME, COMPONENT, INSTANCE).
Returns: Array of result objects for each operation.
Inputs: entries, entry.
set_guideC
Add or delete one or more guides on the current Figma page.
Returns: Array of result objects for each operation.
Inputs: guide, guides.
set_imageAIdempotent
Sets or inserts one or more images into Figma. Each image can be specified by a remote URL, a local file path, or a base64 data URI. Accepts either a single image config (via 'image') or an array of configs (via 'images'). You can customize size, name, and parent node.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the inserted image node ID(s).
Inputs: image, images.
set_maskAIdempotent
Applies a mask in Figma. Supports single or batch:
Single: { targetNodeId, maskNodeId, channelId? }
Batch: { operations: [ { targetNodeId, maskNodeId, channelId? }, ... ] } Returns an array of result objects.
Inputs: maskNodeId (required), operations (required), targetNodeId (required), channelId, +1 more.
set_matrix_transformADestructive
Set a transformation matrix on one or more Figma nodes (single or batch).
Parameters:
entry: { nodeId: string, matrix: number[] } (optional, for single)
entries: Array<{ nodeId: string, matrix: number[] }> (optional, for batch)
options: { skipErrors?: boolean } (optional)
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the result for each node.
Inputs: entries, entry, options.
set_nodeB
Sets or inserts one or more child nodes into parent nodes at optional index positions in Figma.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the parentId, childId, index, success status, and any error message.
Inputs: childId, index, operations, options, +1 more.
set_node_propB
Sets node properties (locked, visible, etc.) for one or more nodes.
Inputs: no named parameters.
set_pageB
Create, delete, rename, or set current page (single or batch).
Returns: Array of result objects for each operation.
Inputs: no named parameters.
set_selectionD
Inputs: inputSchema (required).
set_svg_vectorAIdempotent
Sets or inserts one or more SVG vectors in Figma. Accepts either a single SVG config (via 'svg') or an array of configs (via 'svgs').
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the inserted SVG vector node ID(s).
Inputs: svg, svgs.
set_textAIdempotent
Creates one or more text elements in Figma. Accepts either a single text config (via 'text') or an array of configs (via 'texts'). If 'width' and 'height' are provided, creates a bounded text box; otherwise, creates a regular text node.
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the created text node ID(s).
Inputs: text, texts.
set_text_contentBIdempotent
Sets the text content of one or more text nodes in Figma. Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the update result.
Inputs: nodeId, text, texts.
set_text_styleAIdempotent
Sets one or more text style properties (font, size, weight, spacing, case, decoration, etc.) on one or more nodes in Figma. Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the update result.
Inputs: entries, nodeId, styles.
set_variableAIdempotent
Creates, updates, or deletes one or more Figma Variables (design tokens).
Returns:
content: Array of objects. Each object contains a type: "text" and a text field with the result or summary.
Inputs: ids, variables.
set_variantC
Create, add, rename, delete, organize, or batch create variants/properties in a component set (single or batch).
Returns: Array of result objects for each operation.
Inputs: variant, variants.
subscribe_eventC
Subscribe or unsubscribe to a Figma event (e.g., selection_change, document_change).
Returns: { subscriptionId } for subscribe, { success: true } for unsubscribe
Inputs: eventType (required), subscribe (required), filter, subscriptionId.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 72 tools
Tools are generally distinct by resource and action (e.g., create_rectangle vs. resize_node), but there is significant overlap in style-setting tools (e.g., set_effect, set_gradient, apply_effect_style) and redundant getters (e.g., get_node_info, get_node_style, get_fill_and_stroke). This overlap could confuse agents about which tool to use for specific styling or info retrieval tasks.
Most tools follow a consistent verb_noun pattern (e.g., create_rectangle, delete_node, get_document_info), with clear action prefixes. However, there are minor deviations like 'boolean' (noun instead of verb_noun) and 'join' (single verb without noun), slightly disrupting the pattern.
With 72 tools, this server is extremely large for a Figma automation domain. While Figma has many features, this count feels excessive and overwhelming, likely leading to confusion and inefficiency for agents. A more focused set of 20-30 tools would be more manageable and appropriate.
The toolset comprehensively covers Figma operations, including creation (e.g., create_frame, create_component_instance), modification (e.g., resize_node, set_text_style), retrieval (e.g., get_node_info, get_svg_vector), deletion (e.g., delete_node), and advanced features like variables and events. There are no obvious gaps for core Figma workflows.
Related MCP Connectors
The Figma MCP server brings Figma design context directly into your AI workflow.
Design canvas for agents: create, edit, render and export Figma-shaped designs over MCP.
Agent-Native design tool - create and edit visual designs with agent assistance
Give your AI agents a design superpower. Generate, edit, and publish publication-grade decks, reports, landing pages, resumes, and marketing visuals directly within your agent workflow. Delivering frontier-level design quality at 3Γ the speed and 53Γ lower cost -from conversational prompt to live link or vector PDF in minutes.
Related MCP Servers
- AlicenseAqualityDmaintenanceAllow your AI coding agents to access Figma files & prototypes directly. You can DM me for any issues / improvements: https://x.com/jasonzhou1993 1. Access all figma pages 2. Access all figma components 3. Access figma prototype flows360 PyPI67MIT
- FlicenseBqualityDmaintenanceEnables AI assistants to interact with Figma files through the ModelContextProtocol, allowing viewing, commenting, and analyzing Figma designs directly in chat interfaces.52,146 npm214-
- FlicenseBqualityDmaintenanceEnables Cursor AI to interact with Figma designs, allowing users to read design information and programmatically modify elements through natural language commands.401,057 npm3-
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that connects AI tools and LLMs to Figma designs, enabling them to extract design data, analyze design systems, and generate development documentation.1,123 npm2MIT