This MCP server provides lookup, free-text search, and product-name classification for Indian HSN/GST codes using a 4,676-entry dataset. It serves these capabilities over an authenticated MCP endpoint for use by MCP clients and agents.
From the registry: Look up Indian HSN and GST codes by description or product name (4,676 entries).
Please install the `hsn-classifier-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Node.js and npm** — Required to run the MCP server launcher via npx. (https://nodejs.org/)
Optional prerequisites:
- Get an API key (optional for free tier) — For paid tiers and authenticated access, obtain an API key from the hosted upgrade flow. Anonymous access is available on the free tier with limited usage. (https://hsn-classifier-mcp.atlasword.workers.dev/upgrade?tier=solo)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@insnapsprakhar/hsn-classifier-mcp"]
Note: Preferred install path is the published npm launcher, which wraps mcp-remote and connects to the hosted endpoint automatically. The README also shows a direct equivalent launcher command: npx -y mcp-remote https://hsn-classifier-mcp.atlasword.workers.dev/mcp --header "Authorization: Bearer <your-api-key>". The hosted MCP endpoint itself uses HTTP POST JSON-RPC with Bearer auth, but the recommended client config is a local stdio launcher. The README does not document any environment variable for passing the API key in the npm launcher form; if authentication is needed, use the direct mcp-remote form with an Authorization header.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.MCP server for searching Airweave collections with natural language queries.