I built an open-source MCP server that gives any AI assistant live NSE + BSE stock data

A developer built and open-sourced an MCP server that provides live NSE and BSE stock data to AI assistants like ChatGPT and Claude. The server runs as a stateless Cloudflare Worker, supporting over 8,200 stocks with fundamentals, technicals, and institutional flows. It implements OAuth authentication and refunds quota for failed API calls due to hallucinated arguments.

Ask ChatGPT or Claude "what was Reliance's operating margin last quarter?" and you get one of two answers: a polite "I don't have live data," or a confident, wrong number. The reasoning is great. The data access is nonexistent — these models are blind to anything past their training cut-off, and they have zero native window into NSE/BSE. So I built an MCP server to fix it, and open-sourced it. This is the build story + a quick-start if you want to plug it into your own setup. The Model Context Protocol is an open standard that lets AI assistants call external tools through a consistent interface. Instead of guessing, the model issues a structured request — get stock quote for RELIANCE — gets real data back, and reasons over it. One protocol, and Claude, ChatGPT, Cursor, Gemini, and Grok can all hit the same data source. It's basically USB-C for AI tools. search stocks screen stocks 326 fundamental filters screen stocks technical get company profile get financials get stock quote get price history get shareholding get fii dii detail market ipo market fno ban get user portfolio add to watchlist ...and 21 more Coverage: all ~8,200 NSE + BSE stocks, fundamentals, technicals, institutional flows, market data, and portfolio tracking. It's a research tool, not a broker — it doesn't place trades. The big one: remote-first, on the edge. ┌─────────────────┐ JSON-RPC / HTTPS ┌──────────────────────┐ │ AI Assistant │ ───────────────────► │ Cloudflare Worker │ │ Claude, etc. │ ◄─────────────────── │ stateless MCP │ └─────────────────┘ └──────────────────────┘ │ D1 users, tokens, usage KV rate limits, auth codes Most MCP servers ship as local stdio processes you have to install and run. That's a friction wall for non-developers. I wanted someone to paste one URL into claude.ai and be done — so the server runs as a Cloudflare Worker. Globally distributed, no servers to babysit. The MCP SDK's WebStandardStreamableHTTPServerTransport in stateless mode maps perfectly onto Workers — any request hits any edge location and is served identically: js const server = createServer env, ph, userId ; const transport = new WebStandardStreamableHTTPServerTransport { sessionIdGenerator: undefined, // stateless enableJsonResponse: true, } ; await server.connect transport ; MCP clients vary wildly. Chat apps Claude.ai, ChatGPT expect a full OAuth flow with Dynamic Client Registration RFC 7591 plus discovery endpoints RFC 8414, RFC 9728 . Code editors often just want a bearer token. The trick that makes the OAuth handshake "just work": return a 401 with a WWW-Authenticate header on the first initialize . That's the signal that kicks off the client's built-in OAuth flow. if authHeader?.startsWith "Bearer " && isPublicMethod { return Response.json { error: "authentication required" }, { status: 401, headers: { "WWW-Authenticate": Bearer resource metadata="${metadataUrl}", scope="openid email" , }}, ; } So the server accepts both short-lived HMAC access tokens and long-lived personal tokens, distinguished by prefix tpt rt … . One auth surface, two credential types. tools/list and ping stay public so registries can discover the catalog without auth. Two independent layers: UPSERT reserves a unit The part I'm happiest with: failed calls get refunded. The MCP SDK throws InvalidParams whenever a tool argument fails schema validation — and LLMs hallucinate bad arguments constantly. Charging a user's quota because their model fumbled an argument would be infuriating. if quotaConsumed && userId { quotaConsumed = false; // guard against double-refund if hasError { ctx.waitUntil refundRateLimitV2 env.DB, userId, date, month ; } else { ctx.waitUntil trackToolCall env.DB, userId, src ; } } For stdio-only clients there's a tiny npm package — ~300 lines, zero runtime deps. No business logic: it reads JSON-RPC from stdin, forwards to the Worker over HTTPS, writes responses to stdout. It auto-detects message framing Content-Length vs newline-delimited JSON, which differ across clients and refreshes the access token before expiry. All tool logic lives on the server, so new tools ship instantly without anyone running npm update . No install claude.ai, ChatGPT, Gemini, Grok — paste the URL, sign in with Google: https://mcp.tapetide.com/mcp Local via npm Cursor, Windsurf, Claude Desktop : { "mcpServers": { "tapetide": { "command": "npx", "args": "-y", "tapetide-mcp" , "env": { "TAPETIDE TOKEN": "your token here" } } } } Then just ask: "Find mid-caps where FII holding rose last quarter, ROE above 15%, and RSI under 40." npx command for reach. .well-known discovery endpoints precisely.Free and open source under MIT. Source, all 34 tools, and setup guides: 🔗 https://github.com/Tapetide-hq/nse-bse-indian-stock-market-data-mcp https://github.com/Tapetide-hq/nse-bse-indian-stock-market-data-mcp If you build something on top of it or have ideas for tools you'd want, I'd love to hear it in the comments.