Design Atlas MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ATLAS_HOST | No | Host for shared HTTP hosting; set to 0.0.0.0 to expose the Node service externally. | |
| CHROME_PATH | No | Path to installed Chrome, used on platforms other than macOS for browser checks and regenerating specimen evidence. | |
| ATLAS_PUBLIC_ORIGIN | No | External origin of the deployment, used when running the HTTP server behind HTTPS. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Search with the actual design problem. Show candidate links and source provenance. Inspect selected references and read instructions.md before rebuilding. Use the existing brand brief and create_brand_kit for an implementation. The library and tools run locally.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_inspirationsB | Find authored reference studies. Present the returned candidates with source links, then inspect the selected ID. Continue with nextSearchArguments. |
| get_inspirationA | Inspect a selected reference. Returns an actual PNG or seven ordered frames, plus a versioned source manifest. Set includeImages to false for metadata only. |
| read_inspiration_bundleB | Read a versioned file. Text offsets count Unicode code points. In transfer mode, concatenate decoded base64 byte chunks and verify the complete SHA-256. |
| read_inspiration_sourceC | Read numbered source lines. Continue with nextOffset in the current range, then nextStartLine at offset zero. |
| search_vaultC | Find implementation-ready snippets and interaction studies by task, category, pack and platform. |
| get_vault_resourceC | Get source and an implementation prompt, supporting documentation, or extras for a Vault ID. |
| get_reference_guideC | Open the official provider workflow for an upstream reference. Returns vetted links and native MCP handoff instructions for Details, Mobbin and design-system sources. |
| list_design_packsA | List visual systems with their principles and number of linked patterns. |
| get_design_packB | Read a pack’s appearance tokens, principles and reference IDs. |
| list_flowsC | Find multi-screen journeys with steps, goals and failure states. |
| get_flowB | Get ordered steps, reusable pattern IDs and recovery considerations for a product journey. |
| list_icon_packsA | List installed SVG families with versions, counts and attribution. |
| search_iconsB | Search local SVG names and families. Use the exact returned pack and name with get_icon. |
| get_iconB | Get the complete inline SVG, its upstream version, license text and accessible usage. |
| import_brand_identityA | Extract declared brand colors, font families, radius, name and description from supplied HTML or CSS. Returns the evidence, unknowns and a brief for create_brand_kit. Runs locally. |
| create_brand_kitB | Build a brand-specific responsive kit. Default returns the source manifest, tokens and contrast checks. Repeat the same brief with output=file and one manifest path to receive its content. Full returns the whole kit. |
| audit_designB | Inspect supplied HTML, CSS and copy for actionable issues. Returns evidence, fixes and scope. |
| remix_inspirationsC | Build from a reference, extract a named detail, generate three side-by-side variations, or combine selected sections with attributable motion. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| design_from_brief | Use source-grounded references to design for a new brand. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| library | Available design and icon packs and flows. |
TDQS
Scored across 18 tools
The set is organized into clearly separated domains (icons, brand, audit, inspirations, vault, flows, packs), and each tool names a distinct resource plus action. The main soft spots are the parallel retrieval triples (search_inspirations/get_inspiration vs search_vault/get_vault_resource) and the read_inspiration_bundle/read_inspiration_source pair, which an agent could pick wrongly, plus remix_inspirations which bundles four different behaviors into one tool.
All names are snake_case verb_noun and follow the list_/search_/get_/read_/create_ pattern per resource domain, which is highly predictable. Minor deviation: 'get' and 'read' are both used for retrieval-style tools (get_inspiration vs read_inspiration_source), blurring the verb semantics slightly.
Eighteen tools is slightly above the ideal range but justified by the breadth of the domain: icons, brand kits, audits, inspirations, vault snippets, reference guides, packs and flows. Each tool corresponds to a real operation, with only marginal redundancy in the inspiration reading tools.
Coverage is strong across every sub-domain: listing, searching and fetching for icons, inspirations, vault resources, designs packs and flows, plus creation and auditing workflows (import_brand_identity, create_brand_kit, audit_design, remix_inspirations) and chunked file reads for large bundles. No obvious dead ends for the read/reference-oriented purpose of this server.