Agent Academy

Agent Academy is a free, source-linked library of skills, prompts, MCP servers and bot templates, organised into courses by profession, for people who hand real work to AI agents: 1,467 live resources, each with its original link, license and safety tags.

MCP server

Figma MCP

Figma MCP: list frames in a file and fetch one frame's JSON and image safely. 2 tools.

Needs credentialsDoes not send
Open the original

https://github.com/scalably-io/figma-mcp

Needs credentials

FIGMA_TOKEN, FIGMA_API_BASE_URL, FIGMA_REQUEST_TIMEOUT_MS, FIGMA_MAX_JSON_BYTES, FIGMA_MAX_FRAME_BYTES, FIGMA_OUTPUT_ROOT, FIGMA_ALLOW_HTTP_FOR_TESTS

Install
npx -y @scalably-io/figma-mcp

Original content

Full originalMITSource

Republished in full under its license, with attribution. The source is authoritative.

Figma MCP

Figma REST API MCP server. 2 tools list the top-level frames in a file and fetch one frame's rendered PNG plus its node JSON and image-fill map into a local output directory.

Install

Claude Code:

claude mcp add figma -e FIGMA_TOKEN=your-token -- npx -y @scalably-io/figma-mcp

Codex:

codex mcp add figma --env FIGMA_TOKEN=your-token -- npx -y @scalably-io/figma-mcp

Claude Desktop: download figma-mcp.mcpb from the latest GitHub release and open it.

Setup

  1. Create a personal access token at figma.com under account settings, with file_content:read scope.
  2. Find the file key in any Figma file URL: it is the segment after /design/ or /file/, for example https://www.figma.com/design/AbC123xyz/My-file gives AbC123xyz. Both tools take it as file_key.
  3. If FIGMA_TOKEN is not set the server still starts and lists its tools; every call then fails with FIGMA_NOT_CONFIGURED until the token is provided.
  4. fetch_frame is the only tool that writes files (so it is not marked read-only); it writes frame.png, node.json, and fills.json into a directory below the configured output root (default ./figma-output). The other tool is fully read-only.

Tools (2)

ToolWhat it does
list_framesList and optionally filter all top-level FRAME nodes in a Figma file, with exact page/name/node-id data, dimensions, and file metadata
fetch_frameFetch one Figma frame and transactionally write frame.png, node.json, and a normalized image-fill map into a directory below the output root

Configuration

VariableRequiredPurpose
FIGMA_TOKENyesFigma personal access token with file_content:read
FIGMA_API_BASE_URLnoOverride the Figma REST API base URL (default https://api.figma.com/v1)
FIGMA_REQUEST_TIMEOUT_MSnoPer-request timeout in milliseconds (default 60000)
FIGMA_MAX_JSON_BYTESnoUpper bound on a Figma JSON response, in bytes (default 104857600)
FIGMA_MAX_FRAME_BYTESnoUpper bound on a downloaded frame PNG, in bytes (default 104857600)
FIGMA_OUTPUT_ROOTnoDirectory that every fetch_frame output directory must stay below (default ./figma-output, created on first use)
FIGMA_ALLOW_HTTP_FOR_TESTSnoTest suite only: 1 allows a plain-HTTP loopback API base. Never set it in normal use

Reply shape

Every tool returns plain JSON with status (succeeded, partial, no_op), summary, target, result, proof, warnings, recovery. Failures throw a plain error string: : <message> <hint>.

Limits

fetch_frame renders through Figma's image API, so very large frames or extreme scale values can exceed the configured JSON or frame byte limits; lower scale or split the frame if that happens. fills.json URLs are temporary and expire within 14 days.

Verify

Each release lists the package version, the .mcpb sha256 and the production commit it was derived from in CHANGELOG.md. CI runs the tests and a clean install of the packed tarball on every push.

Privacy Policy

This server runs locally, on your machine, under your own credentials. It collects no personal data, contains no telemetry, stores nothing persistently beyond the frame bundles you explicitly fetch, and talks only to the vendor API it wraps. No third party, including Scalably, receives your data. Contact: hello@scalably.io. Canonical copy: https://scalably.io/connector-privacy.html

License

MIT. Copyright Scalably.

DescriptionFigma MCP: list frames in a file and fetch one frame's JSON and image safely. 2 tools.
Version1.0.1
Packagesnpm · @scalably-io/figma-mcp@1.0.1 · stdio
mcpb · https://github.com/scalably-io/figma-mcp/releases/download/v1.0.1/figma-mcp.mcpb · stdio
Environment variablesFIGMA_TOKEN required secret
Figma personal access token with file_content:read
FIGMA_API_BASE_URL
Figma REST API base URL, default https://api.figma.com/v1
FIGMA_REQUEST_TIMEOUT_MS
Per-request timeout in milliseconds, default 60000
FIGMA_MAX_JSON_BYTES
Upper bound on a Figma JSON response in bytes, default 104857600
FIGMA_MAX_FRAME_BYTES
Upper bound on a downloaded frame PNG in bytes, default 104857600
FIGMA_OUTPUT_ROOT
Directory that all fetch_frame output directories must stay below, default ./figma-output
FIGMA_ALLOW_HTTP_FOR_TESTS
Test suite only: set to 1 to allow a plain-HTTP loopback API base. Never set it in normal use
Websitehttps://scalably.io/mcp/figma-mcp

Related

Design systemDesign

Apple Human Interface Guidelines

Apple's platform design guidance: foundations, patterns, components, inputs, technologies.

Sourcedeveloper.apple.com/design/human-interface-guidelines

No credentialsDoes not sendApple terms; link only
Style libraryDesign

UI Hub (Incidental AI UI resource hub) — llms.txt / api

Curated multilingual directory of ~2,391 public UI resources with visual-style (vs) facets, design KB (specs, skills), JSON endpoints and a recommended design-skill workflow.

Sourcesiinxu.github.io/ui-resource-hub/llms.txt

No credentialsDoes not sendaggregator; per-item license
WorkflowDesign

UI Hub skills.json (recommended design workflow)

Workflow: pick ONE direction skill (frontend-design or taste-skill) → search resources by style/kind → build with emil-design-eng → audit with impeccable + web-design-guidelines + accessibility → verify in browser light+dark, mobile.

Sourcesiinxu.github.io/ui-resource-hub/api/skills.json

No credentialsDoes not sendaggregator
SkillDesign

algorithmic-art

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

Sourcegithub.com/anthropics/skills/blob/main/skills/algorithmic-art/SKILL.md

No credentialsDoes not sendApache-2.0
SkillDesign

canvas-design

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

Sourcegithub.com/anthropics/skills/blob/main/skills/canvas-design/SKILL.md

No credentialsDoes not sendApache-2.0
CaseDesign

Multimodal Design Agent Team

A Streamlit application that provides comprehensive design analysis using a team of specialized AI agents powered by Google's Gemini model.

Sourcegithub.com/Shubhamsaboo/awesome-llm-apps/tree/main/advanced_ai_agents/multi_agent_apps/agent_teams/multimodal_design_agent_team

No credentialsDoes not sendApache-2.0