figmingo-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FIGMA_API_KEY | Yes | Your Figma Personal Access Token. Get one from Figma Settings > Security > Personal access tokens. |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_design_contextA | Get the simplified design context for a Figma file or node: layout (absolute bounds, auto-layout), fills/strokes/effects, and text styles. Use format=compact for a small token footprint. |
| get_metadataA | Lightweight tree of a Figma file/node (id, name, type, bounds) for orientation before a deep fetch. Output as XML (default) or JSON. |
| get_screenshotA | Render a Figma node to an image via GET /v1/images/:fileKey (scale 0.01–4, png|jpg|svg|pdf). Returns the image inline (base64) and/or saves it to disk. |
| download_assetsA | Batch-export nodes as files (up to N ids, chunked) plus raw image fills from GET /v1/files/:key/images. Saves everything into a directory and returns a manifest. Temp Figma URLs are downloaded immediately and cached. |
| get_variable_defsA | Get design tokens: tries the Enterprise variables/local endpoint first; on 403 falls back to published styles + tokens inferred from node fills/text styles. Every output is marked with source. |
| search_design_systemA | Search the file's design system: components, component sets, and published styles. Local index, no extra API quota beyond one file fetch. |
| get_code_connect_mapB | Read figmingo.components.json (local component→code mapping) and return the code targets for components found in the requested node subtree. |
| whoamiA | Token sanity check via GET /v1/me, plus rate-limit observations and disk-cache status. |
| get_html_replica_specB | Build a replica-optimized spec from a Figma file/node: sections/elements with absolute rects, computed typography (family/style/size/letter-spacing/line-height/text-case), hex+alpha colors, gradient data, and an asset manifest (icons→svg, image fills→urls, logo hints). Output schema matches verify_html_parity input. |
| render_html_screenshotA | Playwright (chromium) screenshot of a local/remote HTML page or an element selector. Waits for images to load, can hide fixed/sticky elements, supports full-page or selector-local captures. |
| verify_html_parityA | The acceptance gate. Compares rendered HTML against a Figma replica spec: content gate (copy/font/color tolerances: font size ±1px, letter-spacing ±0.5px, line-height ±2px, color ±2/255), structural gate (position/size ±4px), visual gate (pixelmatch diff ratio ≤ 1%, 2px crop tolerance). Emits a JSON report + diff images. |
| compare_html_to_imageA | One-shot visual comparison: renders an HTML page/element with Playwright (chromium) and pixel-diffs it against a reference image (e.g. a Figma export). passed = diffRatio <= maxRatio (default 0.01 = 1%; raise maxRatio for rework/triage loops where you only need localization, not a strict gate). Returns diff ratio, anti-alias accounting (see methodology in the response), and per-band diff localization — equal-height bands or custom bandEdges so one band can map to one design element. Replaces the manual render_html_screenshot → write-a-diff-script two-step. |
| bridge_statusA | Is the figmingo companion plugin connected? Reports client info, pending/queued command counts, and the bridge address. |
| execute_plugin_commandA | Send a command envelope to the companion Figma plugin over the local bridge. Commands: create_frame, create_text, create_rectangle, set_fills, set_effects, set_auto_layout, insert_image, move_node, resize_node, delete_node, get_selection, get_file_info, get_page_children, export_node. Use |
| import_html_replicaA | Import an HTML page or a replica spec into Figma as native frames via the plugin bridge. Give it an HTML file (htmlPath) or URL (htmlUrl) and it extracts layout + computed styles with headless Chromium, then rebuilds: main frame → section frames → nested containers / text / image nodes with absolute positions, border-radius, borders, shadows, gradients, and real image bytes. Alternatively pass a ready-made spec (spec/specPath, from get_html_replica_spec or hand-written). All degradations (missing fonts, SVG assets, failed images) are reported in the warnings array. Supports dryRun to preview the command plan. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/wenym8/figmingo-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server