
Connects Claude to Figma through Pipeworx's gateway infrastructure. The server uses streamable HTTP transport and can be added to any MCP client with a single URL endpoint. You can either connect directly to the Figma-specific endpoint or use the full Pipeworx gateway for access to 725+ data sources. Includes an ask_pipeworx tool that lets you query Figma data in plain English instead of calling specific tools directly. The gateway handles tool selection and argument mapping automatically. Useful if you want to pull design data, file information, or team resources into Claude without managing authentication flows yourself. Part of the broader Pipeworx MCP ecosystem with MIT licensing.
Figma MCP Pack
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
| Tool | Description |
|---|---|
get_me | Get the signed-in Figma user: id, email, handle, and avatar image URL. Use to identify whose Figma account is connected. |
get_file | Get a compact summary of a Figma design file by its file key: name, last modified time, version, editor type, role, thumbnail URL, and the list of top-level pages (id, name, type, child count). Use to understand the structure of a Figma design file without fetching the full node tree. |
list_comments | List comments on a Figma design file. Returns each comment's id, message, author handle, created time, and resolved time. Use to review feedback and discussion on a design. |
get_file_nodes | Get specific nodes from a Figma design file by their node ids. Returns a compact map of node id to { name, type }. Use to inspect particular frames, components, or layers within a design file. |
get_file_images | Render images of specific nodes in a Figma design file. Returns a map of node id to a rendered image URL. Use to get visual previews (PNG, SVG, or JPG) of frames, components, or layers from a design. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"figma": {
"url": "https://gateway.pipeworx.io/figma/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/figma/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Figma data" })
The gateway picks the right tool and fills the arguments automatically.
MIT
This pack runs against a connected figma account, so it needs a Pipeworx key: sign in at https://pipeworx.io/account, connect figma, then call POST https://gateway.pipeworx.io/v1/tools/figma_get_me with Authorization: Bearer <your Pipeworx key>. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/figma_get_me. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.