Loading…
Live React design-system APIs, patterns, and code validation for accurate UI generation.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 1 month ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The design-system-mcp MCP server exposes 14 tools, focused primarily on AI capabilities. Its published description reads: "Live React design-system APIs, patterns, and code validation for accurate UI generation". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates design-system-mcp F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Cross-tool shadowing" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check design-system-mcp's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add design-system-mcp to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://mcp.marmoui.com/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Returns the MCP knowledge version: gitSha, indexedAt, componentCount, patternCount, uptimeSeconds. Call this ONCE per session before generating UI code so you know how fresh the design-system data is.
MANDATORY FIRST CALL before writing any @marmoui/ui code in this session. Returns a step-by-step generation checklist (which tools to call, in what order), critical rules (no namespace sub-components,
List all available @marmoui/ui components with names, descriptions, categories, and prop counts. Use to discover what exists. Prefer `search_components` when you already know the use case (form, table
Search @marmoui/ui by keyword (e.g. "form", "table", "dialog", "avatar"). Preferred discovery tool — returns the 5-8 most relevant components for a need. Call this before `get_component_info` when uns
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: get_design_guidelines
A tool description tries to alter the model’s use of another tool.
e SAME value to review_generated_code so it enforces it. Ask the user which icon librRecommendationDescriptions must describe only their own tool.
tool: list_components
A tool description tries to alter the model’s use of another tool.
exists. Prefer `search_components` when you already know the use case (form, tablRecommendationDescriptions must describe only their own tool.
tool: search_components
A tool description tries to alter the model’s use of another tool.
ll this before `get_component_info` when unsure which component to use.RecommendationDescriptions must describe only their own tool.
tool: get_pattern
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
full page), app-shell, confirmation-dialog, dialogs-for-other-actionsRecommendationAnnotate destructive tools and require human approval.
tool: review_generated_code
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "context"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: review_generated_code
A tool description tries to alter the model’s use of another tool.
t you passed to get_design_guidelines; wrong-library icon imports are ERRORS). If valRecommendationDescriptions must describe only their own tool.
tool: validate_component_usage
A tool description tries to alter the model’s use of another tool.
es[]}`. Prefer `review_generated_code` for post-generation review (it also auto-fixesRecommendationDescriptions must describe only their own tool.
tool: generate_component
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: validate_component_usage
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "validate_component_usage"RecommendationScope tools to the minimum needed.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Get exact props (with types and defaults), code examples, composition patterns, and common mistakes for a single @marmoui/ui component. REQUIRED before using any component for the first time in a sess
Get a complete, validated composition example for a common UI pattern. Available: app-layouts (ASK USER which of 4 layout ids before any full page), app-shell, confirmation-dialog, dialogs-for-other-a
⚠️ MANDATORY — call this on every piece of code you generate before returning it to the user. Validates TSX/JSX against real @marmoui/ui prop signatures and returns { valid, errors[], warnings[], sugg
Validate a TSX/JSX snippet against real @marmoui/ui prop signatures. Returns `{valid, issues[]}`. Prefer `review_generated_code` for post-generation review (it also auto-fixes namespace patterns and s
Returns the authenticated tenant's customized theme tokens, CSS variables export, and component overrides. Call after auth to apply tenant-specific styling in generated code.
Generate a portable DESIGN.md for the authenticated tenant — brand color, type, tokens, and component inventory — that any AI agent can read to generate on-brand UI. Pass format="markdown" (default) f
Validate and optionally save a custom component for the authenticated tenant. Runs review_generated_code validation before persisting. Use for AI-generated or customized components.
Returns ready-to-paste MCP configuration for Cursor, Claude Code, or Codex. Use on the Connect page or when setting up a new project.
Register a prototype for sharing and get a share URL. Reviewers can leave inline comments via the Marmo overlay.
Fetch inline comments from a shared prototype as structured data and Markdown. Pull into Cursor/Claude to iterate on feedback.