svelte5

The Svelte 5 MCP Server provides a searchable, knowledge-backed assistant for Svelte 5 development. It hosts a curated knowledge base and a library of code examples, enabling you to ask for explanations of Svelte 5 concepts, retrieve patterns, and generate components using runes like $state, $derived, and $effect. Core tools include search_knowledge for concept explanations, search_examples for code patterns, generate_with_context to scaffold components from curated patterns, audit_with_rules to review code against best practices, and explain_concept for in-depth guidance with examples. To integrate with your workflow, configure your MCP client to point at the server and invoke these tools through the provided prompts and queries, such as searching for runes or generating a new component using specified features.

Prerequisites:

• Node.js and npm installed on your system
• A Git client
• Basic familiarity with MCP clients/configuration

Installation steps:

1. Clone the repository

git clone <repository-url>
cd svelte5-mcp-server

2. Install dependencies

npm install

3. Build the server

npm run build

4. Start the server

npm start

Notes:

• The server uses a SQLite database with FTS5 for fast search. Ensure your environment has the necessary build tooling for TypeScript.
• If you customize prompts or data, place them under data/ as described in the project documentation.

Tips and considerations:

• The server relies on a knowledge base at data/svelte_5_knowledge.json and code patterns at data/svelte_5_patterns.json. Ensure these files are valid JSON to avoid startup errors.
• When integrating with a MCP client (e.g., Claude Desktop), point the client to the appropriate command path and arguments, typically like: {"command":"node","args":["/path/to/dist/index.js"],"env":{}}.
• If you encounter "No results found" or "Tool not found", verify the server is built and running, and confirm the MCP client configuration matches the server name (svelte5).
• For debugging, enable verbose logs (e.g., DEBUG=* npm start) and check the server logs for startup errors or misconfigurations.
• The server supports environment customization via env variables; consider setting variables for API keys, data paths, or logging levels as needed.