Seedwall MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SEEDWALL_URL | No | The Seedwall instance to call. | https://seedwall.suryansh.work |
| SEEDWALL_MCP_URL | No | Overrides the plugin's server URL. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Seedwall makes deterministic generative art (wallpapers, hero backgrounds, banners, cover images) as SVG or PNG. Every image is a pure function of (look, preset, params, size, seed): the same inputs always give the same image, so URLs are stable and safe to embed. Workflow: list_looks to choose a look → describe_look for its params (colours, density, text) → render to get image URLs and a preview. For website backgrounds, pass text_free: true (the page puts its own headline on top) and the page's brand colours as params.
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 |
|---|---|
| list_looksA | Lists every Seedwall look (generator) with its presets, plus the colour themes and device sizes you can render with. Call this first to pick a look. |
| describe_lookA | Shows one look's parameters (colours, shapes, density, text layer) and its presets, so you can set params when rendering. |
| renderA | Renders a look at any size and returns stable SVG and PNG URLs, a link to keep editing it in the Seedwall studio, and a small preview image. Use it for website heroes, section backgrounds, OG/social images, banners, blog covers, or wallpapers. |
| seedB | Every number from 1 to 999999 is one fixed Seedwall image, the same for everyone. Omit seed for today's daily wallpaper. Good for 'surprise me'. |
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 4 tools
list_looks and describe_look are clearly split (all looks vs. one look's parameters), and render is a distinct parameterized generation tool. The only blurry boundary is seed, whose name reads like a render parameter and whose relationship to looks is unspecified, so an agent could hesitate between render and seed for a 'random image' request.
list_looks and describe_look follow a clean verb_noun pattern, but render drops the object and seed is a bare noun that doesn't follow the verb convention at all. The names remain readable, but the set mixes conventions rather than holding one pattern.
Four tools for a focused render/discovery service is lean but defensible: discovery (list/describe) plus two generation entry points. It is slightly thin, and seed arguably duplicates a mode that could live inside render, but nothing is bloated.
The core lifecycle is covered: discover looks and themes/sizes, inspect parameters and presets, then render to SVG/PNG with a studio edit link or grab a fixed/daily seed image. Minor gaps exist — no explicit standalone enumeration of sizes/themes, no way to combine a seed with a specific look, and no batch render — but agents can work around them.