figma-reader-mcp
Related Servers
Alternatives to figma-reader-mcp
No user-submitted related servers found.
Related Servers
- AlicenseAqualityBmaintenanceEnables AI agents to read and inspect local Figma .fig files entirely offline, exposing document structure, geometry, styles, text, components, variables, and embedded images via MCP tools.12275 npm3MIT
- FlicenseNot gradedqualityDmaintenanceRead-only MCP server that wraps the Figma REST API, providing tools like get file metadata, list frames, and export node image URLs for AI SDLC agents.-
- AlicenseNot gradedqualityBmaintenanceEnables agents to extract, inspect, search, and bundle design context from local Figma .fig files entirely offline, exposing frame summaries, node context, style tokens, assets, vector SVGs, and visual-match review via MCP.MIT

Figma MCP Serverofficial
FlicenseNot gradedqualityBmaintenanceProvides Figma design context to AI agents, enabling code generation, design system integration, and canvas manipulation through MCP.2,129-- FlicenseNot gradedqualityBmaintenanceEnables AI agents to access Figma design context, generate code from frames, extract variables, components, and layout data, and create or modify Figma files directly from MCP clients.-
- FlicenseNot gradedqualityDmaintenanceMCP server for the Figma API. Lets AI agents fetch designs, nodes, and rendered images from Figma.3,295 npm-
TDQS
Scored across 18 tools
Most tools target clearly distinct resources or actions (get_text, get_styles, get_variables, search, screenshot, diff, changes). Some overlap exists among node-inspection tools (get_node, get_tree, locate) and token-related tools (get_styles, get_variables, token_usage), but the descriptions carefully distinguish their scopes and output formats.
All names share a consistent figma_ prefix and snake_case formatting with mostly verb_noun patterns. A few are noun phrases (figma_screenshot, figma_status, figma_changes) or noun-based (figma_dev_status, figma_token_usage), which is a minor deviation from a strict verb_noun convention.
Eighteen tools is slightly heavy for a read-only Figma reader, but each covers a genuinely distinct part of the domain (loading, tree/node inspection, text, styles, variables, components, search, screenshots, image exports, diffs, change history, account state). The breadth justifies the count more than it bloats the surface.
The surface covers the core read lifecycle very well: export/load, inspect nodes and text, extract styles/variables/components, search, screenshot, export image fills, diff snapshots, and track changes. Minor gaps exist, such as reading Figma comments or version metadata, but agents can work around them for typical read-only tasks.