Figma Context MCP AIR vs UI Design to Code
A side-by-side look at the Figma Context MCP AIR and UI Design to Code MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Figma Context MCP AIR for architecture & design work as a local process; choose UI Design to Code for architecture & design as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Figma Context MCP AIR when
- You need dedicated capabilities in the Architecture & Design domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
FIGMA_API_KEY, FIGMA_OAUTH_TOKEN, PORT, OUTPUT_FORMAT, SKIP_IMAGE_DOWNLOADS, NODE_ENV. - You want tools like
download_figma_images, get_screenshot, get_metadata.
Choose UI Design to Code when
- You need dedicated capabilities in the Architecture & Design domain.
- You prefer a local stdio subprocess transport.
- You want tools like
get_run_modes, create_design_run, ingest_image_source.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Architecture & Design | Architecture & Design |
| Quality signal | 51/100 · Good | 52/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | FIGMA_API_KEYFIGMA_OAUTH_TOKENPORTOUTPUT_FORMATSKIP_IMAGE_DOWNLOADSNODE_ENV | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 1 | 0 |
| Directory activity | 2 views 0 installs 0 upvotes | 0 views 0 installs 0 upvotes |
| Tools | 7 | 14 |
| Full listing | View Figma Context MCP AIR | View UI Design to Code |
Tools & capabilities
Figma Context MCP AIR tools 7
download_figma_imagesDownloads PNG or SVG renders of Figma nodes to your local filesystem.get_screenshotCaptures a Figma node as a 2x PNG and saves it to disk. Useful for visual validation.get_metadataReturns a sparse XML representation of the node hierarchy (depth=2). Use this for quick layer discovery before fetching full design context.get_variable_defsFetches all design tokens from a Figma file — variable collections (colors, spacing, typography) and published styles (effects, text styles, fill styles). Returns data with CSS custom property syntax.whoamiReturns the authenticated user's Figma account information (name, email, plan tier). Useful for verifying your API key is working.create_design_system_rulesGenerates a comprehensive markdown template for project-specific design system rules. Tailored to your language and framework combination. Save the output to `CLAUDE.md` or your project's AI instructions file.get_figjamExtracts content from a FigJam board — sticky notes, connectors, shapes, sections — as XML with screenshot URLs.
UI Design to Code tools 14
get_run_modesReturns supported modes, target platforms, trigger examples, and the mode-selection prompt.create_design_runCreates the run directory and `artifact-run-manifest.json`.ingest_image_sourceRegisters a screenshot or image into:ingest_figma_sourceRegisters Figma MCP node JSON, an optional screenshot, or both.slice_image_assetsCrops bitmap/icon assets from a source image using a `layers.manifest.json` with `source_bbox` entries.build_reference_analysisRegisters model-generated Reference Image Analysis before Vision IR. This captures the original pixel size, root frame, semantic top-level groups, text/media/icon/material inventory, bottom navigation, strict extraction settings, high-risk zones, and the audit plan used for later decoding.build_semantic_irRegisters model-generated Platform-neutral Semantic UI IR.build_cross_platform_nodesRegisters Cross-platform Node Data.build_target_irRegisters target-platform layout IR for a selected target.run_codegenRecords implementation output and validation summary without enforcing visual review.run_codegen_with_auto_reviewRecords implementation output plus visual review evidence.validate_pipelineValidates an existing run by checking required artifacts and traceability links between vision, compression, semantic, cross-platform, and target planning artifacts.- +2 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Figma Context MCP AIR
{
"mcpServers": {
"figma-context-mcp-air": {
"command": "npx",
"args": [
"-y",
"figma-context-mcp-air"
],
"env": {
"FIGMA_API_KEY": "YOUR_FIGMA_API_KEY_HERE",
"FIGMA_OAUTH_TOKEN": "YOUR_FIGMA_OAUTH_TOKEN_HERE",
"PORT": "YOUR_PORT_HERE",
"OUTPUT_FORMAT": "YOUR_OUTPUT_FORMAT_HERE",
"SKIP_IMAGE_DOWNLOADS": "YOUR_SKIP_IMAGE_DOWNLOADS_HERE",
"NODE_ENV": "YOUR_NODE_ENV_HERE"
}
}
}
}
UI Design to Code
{
"mcpServers": {
"ui-design-to-code": {
"command": "npx",
"args": [
"-y",
"ui-design-to-code-mcp@latest"
]
}
}
}
Frequently asked questions
Figma Context MCP AIR is categorized under Architecture & Design and uses a local stdio subprocess. UI Design to Code belongs to Architecture & Design and uses a local stdio subprocess. Pick Figma Context MCP AIR for architecture & design work and UI Design to Code for architecture & design.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Figma Context MCP AIR has no declared pricing — check the project's own site. UI Design to Code has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add figma-context-mcp-air and ui-design-to-code as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Figma Context MCP AIR has a quality signal of 51/100 (Good) with 2 views, 0 installs and 1 GitHub stars. UI Design to Code has 52/100 (Good) with 0 views, 0 installs and 0 GitHub stars.