Loading…
Provides Svelte 5 and SvelteKit documentation access with automated content syncing from the official repository, offering both raw and AI-optimized distilled versions with scheduled updates to keep framework documentation current.
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 mcp-typescript server on vercel MCP server exposes 2 tools, focused primarily on general-purpose capabilities. Its published description reads: "Provides Svelte 5 and SvelteKit documentation access with automated content syncing from the official repository, offering both raw and AI-optimized distilled versions with schedu…". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates mcp-typescript server on vercel F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Cross-tool shadowing" and "Metadata dictates tool-call ordering". 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 mcp-typescript server on vercel's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add mcp-typescript server on vercel to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://svelte-llm.stanislav.garden/mcp/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.
Lists all available Svelte 5 and SvelteKit documentation sections in a structured format. Returns sections as a list of "* title: [section_title], path: [file_path]" - you can use either the title or
Retrieves full documentation content for Svelte 5 or SvelteKit sections. Supports flexible search by title (e.g., "$state", "routing") or file path (e.g., "docs/svelte/state.md"). Can accept a single
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: list_sections
A tool description tries to alter the model’s use of another tool.
section via the get_documentation tool. Always run list_sections first for any quRecommendationDescriptions must describe only their own tool.
tool: list_sections
The text tells the model WHEN to call this tool relative to others ("always call first", "before any other tool", "chain to X tool") — a toxic-flow injection that hijacks the agent’s orchestration rather than describing the tool.
mentation tool. Always run list_sections first for any query related to Svelte development toRecommendationTool metadata must describe only the tool, never sequence the agent’s calls.
tool: get_documentation
A tool description tries to alter the model’s use of another tool.
the output from list_sections (which should be called first). Then ask for ALRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: get_documentation
One tool both accesses the filesystem and reaches the network. Combining two capability classes in a single tool widens its blast radius and is the substrate for confused-deputy and exfiltration abuse.
, \"$state\", \"load functions\") or file path (e.g., \"docs/svelte/state.md\"). Supports singRecommendationSeparate filesystem and network capabilities into distinct, independently-scoped 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.