Talk to Figma MCP
Related Servers
Alternatives to Talk to Figma MCP
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to read, analyze, and modify Figma designs, including bulk style updates, accessibility audits, comment triage, and code generation from designs.807 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to read and modify Figma designs programmatically, supporting design analysis, element creation, text replacement, annotations, auto-layout configuration, and prototype visualization through natural language commands.1,908 npmMIT
- AlicenseBqualityDmaintenanceEnables AI assistants to interact with Figma designs programmatically, supporting comprehensive design automation including text manipulation with formatting preservation, batch operations, prototyping, auto-layout configuration, and component management.7519 npm5MIT
- FlicenseBqualityDmaintenanceEnables AI agents to read, inspect, and export Figma designs programmatically. Provides tools for listing components, styles, and exporting assets in various formats.51-
- AlicenseAqualityDmaintenanceEnables AI agents to interact with Figma to create, read, and manage designs using the Figma REST API and a dedicated plugin. It supports advanced features like UI generation from text, webpage reconstruction in Figma, and design token synchronization with codebases.20MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants like Cursor to interact with Figma designs programmatically. Supports reading design information, modifying elements, creating components, managing text content, and automating design workflows through natural language commands.1,303 npmMIT
TDQS
Scored across 44 tools
Most tools target clearly distinct resource+action pairs (create_rectangle vs create_frame vs set_fill_color), but the reading cluster is muddy: read_my_design, get_selection, get_node_info, get_nodes_info, and scan_text_nodes all return overlapping node/selection data. Similarly set_focus and set_selections, and the parallel variants (set_annotation vs set_multiple_annotations) require careful reading to distinguish.
Nearly all tools follow a clean verb_noun snake_case pattern (get_document_info, set_padding, create_text, delete_node). The main deviation is read_my_design, which breaks the pattern with a vague verb and first-person noun; a few others like join_channel and export_node_as_image are slightly irregular but still readable.
44 tools is heavy for the domain and includes granular one-property setters (set_padding, set_item_spacing, set_axis_align, set_layout_sizing, set_layout_mode) that could be consolidated into a single auto-layout configuration tool. Many tools earn their place, but the volume makes selection costly for an agent.
Coverage is broad: reads, shape/frame/text/section creation, styling, auto-layout, components and overrides, annotations, prototyping reactions/connections, node manipulation, selection, export, and channel setup are all present. Minor gaps exist—only rectangle/text/frame creation (no ellipse, line, polygon, or vector), no gradient/effect/shadow tools, and no explicit grouping operation.