Up-to-date library docs pulled directly into your AI context.
Figma
Inspect Figma designs, components, and variables from an agent.
Install Figma
— pick your client, copy, paste.{
"mcpServers": {
"figma": {
"command": "npx",
"args": [
"-y",
"@figma/mcp"
],
"env": {
"FIGMA_ACCESS_TOKEN": "${FIGMA_ACCESS_TOKEN}"
}
}
}
}Paste under mcpServers. Fully quit and reopen Claude after editing.
# export FIGMA_ACCESS_TOKEN=figd_your_token
claude mcp add figma -- npx -y @figma/mcpRun from your repo. Commit .mcp.json to share with your team.
{
"mcpServers": {
"figma": {
"command": "npx",
"args": [
"-y",
"@figma/mcp"
],
"env": {
"FIGMA_ACCESS_TOKEN": "${FIGMA_ACCESS_TOKEN}"
}
}
}
}Global path: ~/.cursor/mcp.json. Reload window after editing.
{
"servers": {
"figma": {
"command": "npx",
"args": [
"-y",
"@figma/mcp"
],
"env": {
"FIGMA_ACCESS_TOKEN": "${FIGMA_ACCESS_TOKEN}"
}
}
}
}VS Code uses the "servers" key (not "mcpServers").
{
"mcpServers": {
"figma": {
"command": "npx",
"args": [
"-y",
"@figma/mcp"
],
"env": {
"FIGMA_ACCESS_TOKEN": "${FIGMA_ACCESS_TOKEN}"
}
}
}
}Open via Cascade → hammer icon → Configure.
{
"mcpServers": {
"figma": {
"command": "npx",
"args": [
"-y",
"@figma/mcp"
],
"env": {
"FIGMA_ACCESS_TOKEN": "${FIGMA_ACCESS_TOKEN}"
}
}
}
}Open via the Cline sidebar → MCP Servers → Edit.
{
"experimental": {
"modelContextProtocolServers": [
{
"transport": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@figma/mcp"
],
"env": {
"FIGMA_ACCESS_TOKEN": "${FIGMA_ACCESS_TOKEN}"
}
}
}
]
}
}Continue uses modelContextProtocolServers with a transport block.
# ~/.codex/config.toml
[mcp_servers.figma]
command = "npx"
args = [
"-y",
"@figma/mcp",
]
env = { FIGMA_ACCESS_TOKEN = "${FIGMA_ACCESS_TOKEN}" }Codex uses TOML. Each server is a [mcp_servers.<name>] subtable.
{
"context_servers": {
"figma": {
"command": {
"path": "npx",
"args": [
"-y",
"@figma/mcp"
]
},
"env": {
"FIGMA_ACCESS_TOKEN": "${FIGMA_ACCESS_TOKEN}"
}
}
}
}Zed calls them "context_servers". Settings live-reload on save.
{
"name": "Figma",
"transport": "stdio",
"command": "npx",
"args": [
"-y",
"@figma/mcp"
],
"env": {
"FIGMA_ACCESS_TOKEN": "${FIGMA_ACCESS_TOKEN}"
}
}Enable Developer mode (paid plans) and enter these values in the UI.
Quick answer
What it does
Reads a Figma file or node tree and returns structured data: nodes, styles, components, variables, and optionally screenshots for visual grounding.
Best for
- Design-to-code generation
- Component implementation
- Design-token extraction
- UI-flow documentation
Not for
- Canvas automation
- Bulk file manipulation
Setup recipe
- 1
Install
Copy the install snippet for your client from the Install section above.
- 2
Set required secrets
Set
FIGMA_ACCESS_TOKENin your shell environment before launching your MCP client. - 3
Try a minimum working prompt
Audit a design system for deprecated components
In my Figma file "Design System v3", list every component whose description starts with `[deprecated]` or whose name ends in `(old)`. For each, return: component name, Figma page, and node id so I can jump to it.Tested with: Claude Desktop, Cursor.
Tools & permissions
Tools list pending verification. The server exposes tools over MCP; we haven’t yet parsed its capability manifest into this page. Check the GitHub repo for the authoritative list.
Security & scope
- Access scope
- Read-only
- Sandbox
- Read access to Figma files the authenticated user can see, via a personal access token (or OAuth for enterprise). No write capability.
- Gotchas
- Personal access tokens are not scoped to specific files — they grant read access to every file the user can open.
- Very large Figma files (thousands of nodes) are returned in chunks; the agent has to paginate.
Agent prompt pack
— copy into Claude, Cursor, or ChatGPT.Recommend the best MCP servers for [task: e.g. documents & content work] in [client: Claude]. Constraints: - Prefer tools that are [official | open-source | read-only] — pick what matters for my use case. - Exclude MCPs that require [e.g. a paid plan, OAuth-only flows, remote-only transport]. - Return at most 3 picks, ranked. For each pick include: 1. One-sentence rationale. 2. The ready-to-paste install snippet for my client. 3. Any required secrets I need to create before installing. Cross-check the top-mcps.com listing: https://top-mcps.com/top-mcps-for-documents-content
Compare Figma MCP vs [Context7 MCP] for the following job: [describe the job, e.g. "let an agent create GitHub issues on bug triage"]. Judge them on: - Setup time and complexity (what a new user hits first). - Auth model (none / API key / OAuth 2.1) and credential risk. - Transport (stdio / Streamable HTTP / SSE) and where the server runs. - Required secrets and the blast radius if they leak. - Operational risk in an unattended agent loop. - Which one is "good enough" for a weekend prototype vs. production. End with one sentence: which should I pick for my scenario, which is: [my scenario]. References: - https://top-mcps.com/mcp/figma - top-mcps.com listing for Context7
Install the Figma MCP server for my [client: Claude] at the default config path for that client. Use the exact install snippet published at https://top-mcps.com/mcp/figma (fetch https://top-mcps.com/mcp/figma.json for the canonical server.json if you can read URLs). Before finishing: 1. Create the required secrets (FIGMA_ACCESS_TOKEN) and put them in the appropriate env block — do not hard-code them. 2. Restart or reload the client so it picks up the new server. 3. Verify the server is connected (green / running state) and at least one tool is listed. 4. If anything fails, read the client's MCP logs and report the exact error — do not silently retry. Confirm when done and list the tools the server now exposes.
Frequently asked questions
What changed
— 2 updates tracked.Refreshed install snippets and fact sheet; verified for 2026.
Initial directory listing.
More Documents & Content MCPs
Other tools in the same category worth evaluating.
Exploring Top MCPs for Documents & Content? See all Documents & Content MCPs →