designfit
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FIGMA_TOKEN | No | Figma personal access token. Required for fetching Figma data by link or fileKey/nodeId; optional if extracting from pasted `/nodes` JSON. |
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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| designfit_validateA | Validate a rendered front-end against its Figma design. Tag each built element with data-designfit-id="", pass the design spec (geometry + tokens, from designfit_extract or relayed from Figma's MCP), the running URL, and the component map. Returns a fidelity score and a machine-actionable fix-list of token, geometry, and presence violations. |
| designfit_extractA | Turn a Figma frame into the design spec designfit_validate expects. Give it a Figma link (https://www.figma.com/design//...?node-id=...), or fileKey + nodeId, and it fetches the node via Figma's REST API using the FIGMA_TOKEN env var; or paste the raw GET /v1/files/:key/nodes response as |
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
The two tools have clearly distinct roles: designfit_extract produces the design spec from a Figma frame, while designfit_validate consumes that spec to check a rendered page. Their descriptions explicitly chain them (extract → validate), leaving no ambiguity about which to call when.
Both tools follow the same `designfit_<verb>` pattern with snake_case, and the verbs (extract, validate) accurately describe each action.
Only two tools for the server's scope, which is borderline thin. The extract/validate pairing is well-chosen, but the surface is minimal and could justify helpers (e.g. token setup, batch validation).
The extract→validate pipeline fully covers the core workflow, from Figma frame to fidelity score and fix-list, including a way to bypass the REST fetch by passing raw nodes. Minor gaps exist around configuration/token setup and reporting, but agents can work around them.