Figma Spec Compressor
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FIGMA_ACCESS_TOKEN | Yes | Your Figma personal access token used to fetch live Figma design data. |
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 |
|---|---|
| compress_figma_jsonB | Compress raw Figma JSON AST into compact agent-ready YAML or Markdown specification with Tailwind classes and token metrics. |
| compress_figma_urlB | Fetch a live Figma file/node via REST API and compress it into compact agent-ready YAML or Markdown specification. |
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 2 tools
Both tools perform the same core operation (compressing Figma data into a spec), so an agent must read descriptions to pick correctly. However, the split is clean and explicit: one takes raw JSON, the other takes a live Figma URL, which makes selection straightforward in practice.
Both names follow the same verb_noun pattern with a shared prefix (compress_figma_json, compress_figma_url). The distinguishing suffix directly reflects the input source, which is exactly the right naming convention here.
Two tools is thin for a server, though it matches the narrow purpose of compressing Figma input. Each tool earns its place by covering a distinct input source, but the surface is minimal enough to feel borderline.
The two main input paths (raw JSON and live URL) are covered, along with two output formats (YAML/Markdown). Minor gaps exist around batch processing, node selection options, or caching, but agents can work around these.