@manansiingh/figma-react-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_react_componentA | Fetch a Figma node and convert it into a production React component with Auto Layout → Flexbox, fills, typography, strokes, and border radius mapping. |
| extract_design_tokensA | Extract all design tokens (colors, spacing, typography, radii) from a Figma node tree into a reusable TypeScript tokens file. |
| generate_mfe_moduleB | Generate a self-contained micro-frontend module from a Figma node, with mount/unmount lifecycle hooks and a widget registry entry. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool targets a distinct output: React component, design tokens, and micro-frontend module. There is no overlap in purpose, so agents can easily select the correct tool.
All tool names follow a consistent verb_noun pattern: generate_react_component, extract_design_tokens, generate_mfe_module. The naming is uniform and predictable.
With 3 tools, the server is tightly scoped to its purpose of Figma-to-code conversion. Each tool covers a distinct and necessary capability without bloat.
The set covers the core workflows: component generation, token extraction, and MFE creation. Minor omissions like asset export or project scaffolding exist, but agents can likely accomplish most tasks with these tools.