Loading…
Provides documentation and code patterns for the Fabkit Svelte 5 UI library, including component props, theming API, and Phosphor icon search.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 27 days 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 fabkit-mcp MCP server exposes 7 tools, focused primarily on general-purpose capabilities. Its published description reads: "Provides documentation and code patterns for the Fabkit Svelte 5 UI library, including component props, theming API, and Phosphor icon search". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates fabkit-mcp F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Metadata dictates tool-call ordering" and "Unguarded destructive tools". 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 fabkit-mcp's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add fabkit-mcp to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://fabkit-mcp.fabricators.dev/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 full list of Fabkit components grouped by category (layout, navigation, form, content, etc.). Use this first to discover what is available.
Returns complete documentation for a single Fabkit component: description, all props with types and defaults, usage examples in Svelte 5 syntax, and important notes.
Full-text search across all component docs. Use when you know what you want to do (e.g. "resizable split", "tabs", "dropdown") but not the exact component name.
Returns the full Fabkit theming API: initTheme() signature, all CSS variables (background, text, border, shadow, action, dimensions), dark mode setup, and fine-tuning with Skeleton props.
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: search_icons
The text tells the model WHEN to call this tool relative to others ("always call first", "before any other tool", "chain to X tool") — a toxic-flow injection that hijacks the agent’s orchestration rather than describing the tool.
from "fabkit". Always use this before writing an icon name. {"type":"object","propertRecommendationTool metadata must describe only the tool, never sequence the agent’s calls.
tool: get_pattern
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
ern name: \"app-shell\" | \"sidebar-layout\" | \"settings-page\" | \"RecommendationAnnotate destructive tools and require human approval.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
ry. Always call list_components or search_components before writing any componeRecommendationDescriptions must describe only their own tool.
tool: (server instructions)
The text tells the model WHEN to call this tool relative to others ("always call first", "before any other tool", "chain to X tool") — a toxic-flow injection that hijacks the agent’s orchestration rather than describing the tool.
component code. Always call search_icons before using any Ph* icon name. Always call get_theminRecommendationTool metadata must describe only the tool, never sequence the agent’s calls.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
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.
Search Fabkit's 1514 Phosphor icons by keyword. Returns matching icon export names (Ph prefix) ready to import from "fabkit". Always use this before writing an icon name.
Returns a complete, ready-to-use Svelte code pattern for common UI layouts built with Fabkit components. Use this to scaffold pages or feature areas quickly.
Lists all available ready-to-use Fabkit patterns with a short description of each.