figwright
Related Servers
Alternatives to figwright
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to read and write Figma designs through a local WebSocket relay, turning Figma selections into framework-aware code and building/editing designs directly on the canvas. Provides 112 MCP tools for bidirectional design-code workflows with support for any MCP client.MIT
- AlicenseAqualityDmaintenanceWrite-side MCP server for Figma — build, edit, and search Figma designs from Claude Code, Cursor, Cline, or any MCP client. Complements Figma's official read-only MCP with 41 tools for tree creation, variables, components, and visual verification.412MIT
- AlicenseBqualityCmaintenanceEnables AI agents to directly control Figma Desktop via MCP, supporting UI creation, editing, prototyping, and variable management with over 60 tools.65915 npm1MIT
- AlicenseNot gradedqualityBmaintenanceLocal MCP server exposing Figma REST API tools to AI agents, enabling file reads, comments, variables, and other resource operations. Works with personal access tokens and integrates with Claude, Cursor, Codex, and more.MIT

desrid-html-to-figmaofficial
AlicenseNot gradedqualityBmaintenanceThis MCP server lets AI agents connect to Figma to read, analyze, create, and modify designs, including elements, styles, assets, and code generation. It works with free Figma accounts and supports parallel multi-agent use across MCP-compatible clients.MIT- AlicenseNot gradedqualityCmaintenanceEnables AI agents to create, modify, and manage Figma designs through natural language commands via a specialized MCP server and plugin bridge. It supports a wide range of operations including element creation, property modification, component management, and accessibility checks.8 npm106MIT
TDQS
Scored across 112 tools
Most tools have a clearly distinct target, and descriptions go out of their way to cross-reference near-neighbors (get_node vs get_design_context, set_text vs set_text_properties vs set_text_range, rename_node vs rename_page vs batch_rename_nodes). Still, there is genuine overlap in the read surface: get_document, get_node, get_design_context, get_nodes_info, get_selection, get_metadata, scan_text_nodes, scan_nodes_by_types and search_nodes all read nodes with subtle scope/detail differences that require careful reading to pick among. That is a lot of overlapping retrieval tools in one namespace.
The verb_noun snake_case convention is followed nearly everywhere (set_fills, create_frame, delete_nodes, bind_variable_to_paint, get_design_context). A couple of compound names (find_replace_text, combine_as_variants) are still readable and in-pattern. No camelCase or style drift.
112 tools is a severe mismatch for a single MCP surface. Even with the batch and map tools justified, the read/scan/node-creation/style/variable/motion splits push this far past what an agent can hold in working context, and the count itself creates selection noise independent of any individual description.
Coverage is exhaustive: creation, mutation, deletion, grouping, variables/modes, styles, prototyping reactions, Motion keyframes, screenshots/exports, project scanning and Figma↔code mapping, plus an atomic batch wrapper. I can't identify a meaningful lifecycle gap for a Figma automation server.