Figma-Context-MCP is a Model Context Protocol server that gives AI coding agents structured information about Figma files, frames, and groups. It is used with Cursor and other supported coding tools to help them implement designs from Figma, and the catalogue entries configure or guide that agent integration.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/glips/figma-context-mcp/claude-mdgit clone --depth 1 https://github.com/GLips/Figma-Context-MCPWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/glips/figma-context-mcp/claude-md)<a href="https://agentmods.dev/instructions/glips/figma-context-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/glips/figma-context-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01982 | $0.01982 |
| Opus 5 | $0.00991 | $0.00991 |
| Sonnet 5 | $0.00396 | $0.00396 |
| Haiku 4.5 | $0.00198 | $0.00198 |
Grade A, and why
Figma-Context-MCP CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
3 near-identical copies found in the catalogue:
- Figma-Context-MCP CLAUDE.md — 100% identical, 0 lines differ
- Figma-Context-MCP CLAUDE.md — 100% identical, 0 lines differ
- Figma-Context-MCP-AIR CLAUDE.md — 92% identical, 14 lines differ
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Framelink MCP for Figma
Framelink MCP for Figma is a Model Context Protocol (MCP) server that gives AI coding tools (Cursor, etc.) access to Figma design data. It fetches Figma files/nodes via the Figma API, simplifies the response to include only relevant layout and styling information, and serves it to AI clients.
Build & Development Commands
pnpm install # Install dependencies
pnpm build # Build with tsup (outputs to dist/)
pnpm dev # Development mode with watch + auto-restart (HTTP)
pnpm dev:cli # Development mode (stdio)
pnpm test # Run Vitest tests
pnpm type-check # TypeScript type checking only
pnpm lint # ESLint
pnpm format # Prettier formatting
pnpm inspect # Run MCP inspector for debugging
Running the Server
pnpm start # HTTP mode (default port 3333)
pnpm start:cli # stdio mode for MCP clients
Running a Single Test
pnpm test -- path/to/test.ts
pnpm test -- --testNamePattern="pattern"
Releasing
Releases are automated via release-please. On merge to main, release-please reads conventional commit prefixes (fix:, feat:, feat!:) and maintains a release PR. Merging the release PR publishes to npm via OIDC trusted publishing.
PR Title Convention
PRs are squash-merged, so the PR title becomes the commit message that release-please parses. Always use Conventional Commit prefixes in PR titles.
Architecture
Entry Points
src/bin.ts— CLI entry point, callsstartServer()src/server.ts— Server initialization, handles stdio vs HTTP mode selectionsrc/mcp-server.ts— Library re-exports for external consumers (createServer,startServer, etc.)src/index.ts— Library exports (extractors, types)
Transport Modes
The server supports two transports (configured in src/server.ts):
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 180 lines · 1,982 tokens per session scan A be0717dfaaef
Figma-Context-MCP CLAUDE.md is an instructions file published in the GitHub repository GLips/Figma-Context-MCP (15,765 stars, last pushed 28d ago), licensed MIT. It adds 1,982 tokens to every session, about $0.0099 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
canicode CLAUDE.md
Instructions for let-sunny/canicode, covering canicode, core goal, target environment, tech stack and project structure.
aiconnect-figma-mcp CLAUDE.md
Instructions for guptaprakhariitr/aiconnect-figma-mcp, covering claude.md, project overview, build & development commands, architecture and mcp server (src/aiconnectmcp/server.ts).
figma-unlimited-mcp AGENTS.md
Instructions for AlexZai007/figma-unlimited-mcp, covering agents.md, what this is, what you cannot do yourself, install and step 1 — run the installer.
figma-unlimited-mcp CLAUDE.md
Instructions for AlexZai007/figma-unlimited-mcp: See AGENTS.md — it is the canonical guide for agents working on or with this repository.
rules-accessibility-handoff CLAUDE.md
Claude Code instructions for saralobo/rules-accessibility-handoff, covering accessibility hand-off system v2.3, visual reference (study first), option b: read the text description (works in all tools), key visual rules (memorize these) and your job: three tasks.
llm-safe-haven CLAUDE.md
Claude Code instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.