Systra Tools MCP
An MCP server providing access to a library of 645 production-ready React, TypeScript, and Tailwind CSS UI components, styles, images, and social media templates. It allows agents to list categories, search for components, retrieve source code (TSX), extract styles, and access media assets via tools like list_components, get_component, and search_images.
Endpoint and access
No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.
https://systra.tools/api/mcpWhat its tools do
13 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.
Checks and signals
Each line is separate evidence, not a trust score.
- Passed Endpoint answered the live check ·
- Passed Official MCP Registry namespace is tied to systra.tools ·
- Passed Endpoint is on the registry namespace domain ·
- Availability 1 of 1 checks passed in 30 days
What you can do with it
- List available UI component categories and counts
- Search for specific React components by purpose
- Retrieve TSX source code for UI elements
- Extract design tokens and styles from websites
Source and maintenance
- Maintenance checked
Protocol and capabilities
- Server
- systra-tools 1.0.0
- MCP protocol negotiated in check
- 2025-11-25
- Tools
- 13 advertised
- Resources
- Not advertised
- Resource templates
- Not advertised
- Prompts
- Not advertised
{
"tools": {
"listChanged": false
}
}Server-provided instructions
Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.
Tools
13 advertised
list_categories — List categories
Lists every component category of the Systra Tools library with its slug, its title and how many components it holds. Start here when the user names a kind of page part (hero, pricing, footer) instead of a component, then pass the slug to list_components. No parameters, works without a key.
{
"type": "object",
"properties": {},
"additionalProperties": false
}{
"title": "List categories",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}list_components — List components
Lists component names, optionally limited to one category, one line each with the name and the category slug. Use it to browse a category before choosing; use search_components instead when you already have a keyword. Returns names only, no source: fetch the code with get_component. Works without a key; without one, the components whose source is free are marked "free".
{
"type": "object",
"properties": {
"category": {
"type": "string",
"description": "Category slug from list_categories, e.g. 'heroes', 'cta', 'pricing', 'forms', 'footer'. Omit it to list every component (more than 600)."
}
},
"additionalProperties": false
}{
"title": "List components",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}search_components — Search components
Finds components whose name or category contains the search term (one term, case-insensitive substring match) and returns their names with the category slug. Use it when you know roughly what you need, such as 'pricing', 'marquee', 'testimonial' or 'countdown'; use list_components to see a whole category. Names are English PascalCase, so short English words match best. Follow up with get_component for the source.
{
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"description": "One keyword or name fragment, e.g. 'hero', 'gallery', 'bento'. Matched against component names and category slugs and titles."
}
},
"additionalProperties": false
}{
"title": "Search components",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}get_component — Get component source
Returns the complete, copy-ready React/TSX source of one component as designed, plus notes on its images and any extra files it needs. Components use Tailwind CSS classes and import react, framer-motion and lucide-react; a few also need gsap or three, which the response names with the install command. Use it once you know the exact name; use get_component_styled instead when the component should take on an extracted brand style. Without a premium key, source comes back for the free components, the first six of every category, which list_components and search_components mark as "free"; other names return a notice on how to get a key.
{
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"description": "Component name as listed by list_components or search_components, e.g. 'OrbitGalleryHero'. Matching ignores case."
}
},
"additionalProperties": false
}{
"title": "Get component source",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}list_styles — List brand styles
Lists the brand styles extracted from real websites with the Systra style extractor: slug, site name, primary and accent colour and heading font. Pass query to search by site name, domain, colour or font, for example 'bakery' or 'Inter'. Use it to find a slug for get_style, get_component_styled or get_recipe. Works without a key.
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Search term (optional). Every word must appear in the slug, site name, domain, colours or fonts. Without it, the 30 newest styles are listed."
}
},
"additionalProperties": false
}{
"title": "List brand styles",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}get_style — Get brand style
Returns every design token of one extracted brand style: colours, font families and sizes, spacing, radii, CSS variables and the generated DESIGN.md (up to 4000 characters). Use it to theme your own code or set up a design system; use get_component_styled when you want one specific component already paired with the style.
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"description": "Style slug exactly as listed by list_styles."
}
},
"additionalProperties": false
}{
"title": "Get brand style",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}get_component_styled — Get component in a brand style
Returns one component's source together with the tokens of a brand style, step-by-step instructions for mapping the component's colours, fonts and radii onto that style, and the colour values the component uses today. Use it instead of get_component when the result should match a specific brand. The server does not rewrite the code; you apply the mapping. Same premium rule as get_component.
{
"type": "object",
"required": [
"name",
"style"
],
"properties": {
"name": {
"type": "string",
"description": "Component name as listed by list_components, e.g. 'GradientHeroSection'."
},
"style": {
"type": "string",
"description": "Style slug exactly as listed by list_styles."
}
},
"additionalProperties": false
}{
"title": "Get component in a brand style",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}list_images — List images
Lists images and a few videos from the Systra Tools media library (all AI-generated), each with a permanent URL to use directly as src, plus title, album and format. Filter by album and format, 100 per page. Use it to browse an album; use search_images to find a motif by keyword. Without a premium key only the free images are returned, three per album.
{
"type": "object",
"properties": {
"page": {
"type": "integer",
"minimum": 1,
"description": "Page of the result, 100 images per page (optional, default 1)."
},
"album": {
"type": "string",
"description": "Album key (optional, German): verlaeufe, abstrakt, surreal, objekte, freisteller, natur, interior, essen, portraet, beauty, hochzeit, menschen, arbeitsplatz, business, industrie, gesundheit, sport, autos, luftfahrt, nachtleben. Without one, every album is returned."
},
"format": {
"enum": [
"landscape",
"portrait",
"square"
],
"type": "string",
"description": "Image format to filter by (optional)."
}
},
"additionalProperties": false
}{
"title": "List images",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}search_images — Search images
Finds images in the media library (all AI-generated) whose title, tags, file name or album contain every word of the query, and returns their permanent URLs, 100 per page. Use it for a motif, such as 'red dress', 'laptop desk' or 'misty forest'; use list_images to browse a whole album. Titles and tags are English, album keys German. Without a premium key only the free images are included.
{
"type": "object",
"required": [
"query"
],
"properties": {
"page": {
"type": "integer",
"minimum": 1,
"description": "Page of the result, 100 images per page (optional, default 1)."
},
"query": {
"type": "string",
"description": "One or more words; every word must match. E.g. 'gradient', 'laptop', 'red dress'."
}
},
"additionalProperties": false
}{
"title": "Search images",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}list_posts — List post templates
Lists the Instagram post templates (1080 x 1350) with slug, name, family and whether they need your own imagery. Each template is a single HTML file that can be rebuilt and exported as an image or a video. Pass query to search by name or purpose, for example 'quote' or 'statistic'. Use it to pick a slug for get_post.
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Search term (optional). Every word must appear in the slug, name, purpose or family. Can be combined with family."
},
"family": {
"enum": [
"klar",
"editorial"
],
"type": "string",
"description": "Family to filter by (optional): 'klar' are calm informational posts, 'editorial' lives on the image and a serif face."
}
},
"additionalProperties": false
}{
"title": "List post templates",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}get_post — Get post template
Returns one post template as working instructions: the full HTML file, an export script to render it locally as PNG or video, and the rules on what may be changed. The server renders nothing; you edit and export the file. Use it after list_posts.
{
"type": "object",
"required": [
"slug"
],
"properties": {
"lang": {
"enum": [
"de",
"en"
],
"type": "string",
"description": "Language of the instructions (optional, English by default)."
},
"slug": {
"type": "string",
"description": "Template slug as listed by list_posts."
}
},
"additionalProperties": false
}{
"title": "Get post template",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}list_recipes — List page recipes
Lists curated page recipes: proven section sequences for complete landing pages (for example SaaS, coaching or a hotel), each with its number of sections and a short purpose. Pass query to search by industry, purpose or section, for example 'hotel' or 'pricing'. Use it when the user wants a whole page rather than one section, then call get_recipe.
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Search term (optional). Every word must appear in the slug, title, description or section names. Without it, every recipe is listed."
}
},
"additionalProperties": false
}{
"title": "List page recipes",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}get_recipe — Get page recipe
Returns one page recipe: the ordered sections with the purpose of each, a composition file where available, and the full source of every section. Pass style to add brand tokens and adaptation instructions. Without a premium key, sections that are not free are named but their source is held back. The answer is long because it contains several complete components.
{
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"description": "Recipe slug as listed by list_recipes, e.g. 'saas-produkt' or 'hotel-stay'."
},
"style": {
"type": "string",
"description": "Style slug from list_styles (optional), to adapt the page to a brand."
}
},
"additionalProperties": false
}{
"title": "Get page recipe",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}Prompts
Not advertised
Resources
Not advertised
90-day uptime
A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.
- 2026-11-07: 1 of 1 checks answered
30-day availability
Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.
- Successful checks
- 1 of 1 (100%)
- Average latency
- 2320 ms
- 95th percentile latency
- 2320 ms
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · probe · passed · 2320 ms · metadata changed · 13 tool(s)
Connect from your client
Each snippet registers the same endpoint; pick the client you use.
Claude Code
claude mcp add --transport http systra-tools-mcp https://systra.tools/api/mcpCodex
codex mcp add systra-tools-mcp --url https://systra.tools/api/mcpCursor
{
"mcpServers": {
"systra-tools-mcp": {
"url": "https://systra.tools/api/mcp"
}
}
}Cline
{
"mcpServers": {
"systra-tools-mcp": {
"type": "streamableHttp",
"url": "https://systra.tools/api/mcp",
"disabled": false
}
}
}VS Code
{
"servers": {
"systra-tools-mcp": {
"type": "http",
"url": "https://systra.tools/api/mcp"
}
}
}Gemini CLI
gemini mcp add --transport http systra-tools-mcp https://systra.tools/api/mcpClaude Desktop
https://systra.tools/api/mcpWindsurf
{
"mcpServers": {
"systra-tools-mcp": {
"serverUrl": "https://systra.tools/api/mcp"
}
}
}Let your agent find its tools
Find servers like Systra Tools MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.
Other developer tools servers
Do you run Systra Tools MCP?
Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.