RepoAI
Browse MCPs

AI Tools MCP Server

Embeddings generation and Svelte development workflow support via MCP.

Data last scanned last week · Reviewed last month

48★ 298TypeScriptMIT

Overview

The AI Tools MCP Server provides utilities for Svelte developers to integrate context into their AI-driven workflows. It includes features for generating embeddings using the Voyage API and provides a structured environment for testing with integrated database and MCP inspectors. The server utilizes a Streamable HTTP transport type. Users can manage the configuration via local environment variables and utilize Drizzle Studio to inspect database states directly during the development process.

Our verdict

With a security score of 48/100, this server is currently classified as high risk. This rating reflects that several critical security aspects, such as OAuth support, read-only mode, and authentication methods, have not yet been editorially reviewed. Given the lack of formal security auditing and its community-maintained status, this tool is best suited for experienced developers working in local, sandboxed development environments rather than production setups.

  • Zero direct dependencies minimize supply-chain surface area.
  • Active development with a commit one day ago.
  • Licensed under the MIT open-source license.
  • Security-critical features like OAuth remain unreviewed.
  • Community-maintained rather than official vendor support.
  • Read-only mode support is not yet verified.

Setup

Claude Desktop
{
  "mcpServers": {
    "ai-tools": {
      "args": [
        "-y",
        "@sveltejs/mcp-mono"
      ],
      "command": "npx"
    }
  }
}

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), then restart Claude Desktop. Some servers require API keys or tokens as environment variables — check the project's README and add an "env" object if needed.

  • No read-only mode — running this grants full read/write access.
  • No built-in authentication — anyone with access to this config can invoke every tool it exposes.

Compatibility

ClientLocalDockerRemoteRead-only
ChatGPT
Claude Desktop
Cursor
VS Code
Windsurf

Frequently asked questions

›What configuration is required for embeddings support?

You must set the VOYAGE_API_KEY environment variable in your .env file.

›Are server logs and list-changed notifications currently supported?

No, these are currently unavailable because the SSE channel is shut down immediately to prevent timeout logs on Vercel.

›How can I inspect the MCP server locally?

You can use the MCP inspector by running the pnpm run inspect command and visiting http://localhost:6274/ using the Streamable HTTP transport type.

›Does the server support elicitation and sampling features?

Yes, these features are supported because they are sent over the same stream as the POST request.

Changelog

Badge

AI Tools MCP Server security score, rated on RepoAI

Maintain this server? Add the live badge to your README.