SiftingIO MCP

This is aModel Context Protocol(MCP) server that puts theSiftingIO market-data SDK(@siftingio/sdk) in reach of your AI assistant. Once it's running, the model can pull live prices, dig through SEC/EDGAR fundamentals, fetch OHLCV bars, look up 13F holdings, check market status, and scan the macro economic calendar — all as tools.

You'll need an API key, which you can grab athttps://sifting.io:

- npm run build— compile TypeScript intodist/.
- npm start— run the compiled server (node dist/index.js) overstdio.
- npm run start:http— run it overStreamable HTTP(node dist/http.js).
- npm run dev/npm run dev:http— run straight from source withtsx, no build step.
- npm test— run thevitestsuite (addnpm run test:watchto keep it running).
- npm run lint/npm run format— ESLint (typescript-eslint) and Prettier.
- npm run typecheck—tsc --noEmit.

SIFTING_API_KEY=sft_... npx @modelcontextprotocol/inspector node dist/index.js

SIFTING_API_KEY=sft_... PORT=3000 npm run start:http # → MCP endpoint at http://127.0.0.1:3000/mcp (POST messages, GET SSE, DELETE session)

MCP_AUTH_TOKEN=s3cret SIFTING_API_KEY=sft_... npm run start:http

claude mcp add --transport http siftingio http://127.0.0.1:3000/mcp

{ "mcpServers": { "siftingio": { "command": "node", "args": ["/absolute/path/to/siftingio-mcp/dist/index.js"], "env": { "SIFTING_API_KEY": "sft_..." } } } }

Paginated tools takecursor/limitand hand back ameta.next_cursorto fetch the next page. Thestocks_*list tools —stocks_filings,stocks_earnings,stocks_insiders,stocks_ownership,stocks_events,stocks_compensation— also understandmax_items: set it and they'll auto-paginate, gathering up to that many items across pages in a single call.

The high-traffic tools (last_trade,last_quote,last_tvl,stocks_profile,stocks_search) come with anoutput schemaand returnstructuredContentalongside the human-readable text, so clients can read them machine-side too.

Every tool also carries MCPannotations. The data tools arereadOnlyHint: true(andopenWorldHint: true, since they reach out to the external API), while the WebSocket tools that change connection state arereadOnlyHint: false,destructiveHint: false.

Results aresize-cappedat roughly 60k characters (seeMAX_RESULT_CHARSinsrc/util.ts). When a heavy endpoint — full XBRL financials, screeners, OHLCV bars — returns more than that, the server trims its largest array and tacks on a_truncatednote explaining how to narrow the query.

Streaming is the awkward case: it doesn't fit neatly into a single request/response. So the server holdsone persistent WebSocketopen, buffers the frames as they arrive, and the tools just read from that buffer. Channels (theproductfield) arecex(crypto),dex(DEX trades),fx(forex),us(US stocks), andtvl(DEX pool TVL).

The connection reconnects on its own and replays your subscriptions when it does. The buffer is a rolling window, so the oldest frames eventually fall off — and when they do, you'll hear about it throughdropped/gap.

These are guided, multi-tool workflows your client can surface as slash-commands:

- company_snapshot(ticker)— pullsstocks_profile,stocks_ratios, the lateststocks_filings, andlast_tradetogether into one briefing.
- compare_companies(tickers)— lines up several tickers side by side across the key ratios.
- market_now— what's open and closed right now, plus the high-impact macro events coming up.

The server advertises the MCPloggingcapability and pushes structurednotifications/messageto the client whenever something happens with the connection (WebSocket open/close/reconnect/error) or on shutdown — and it mirrors all of that to stderr too.

When it catches aSIGINT or SIGTERM, it closes the live WebSocket and shuts the server down cleanly before exiting.

Remote MCP server for historical crypto & prediction-market data: search ~500K instruments, live market stats (OHLC, turnover, spreads, depth, slippage) and tick-data purchase. Keyless for catalog & stats; optional OAuth for account tools. Endpoint: https://cryptostruct.com/mcp

Read-only MCP server for your Evibe investment portfolio + live market data (holdings, performance, dividends, benchmarks, screeners). Works with Claude & ChatGPT.

Alpaca’s official MCP Server lets you trade stocks, ETFs, crypto, and options, run data analysis, and build strategies in plain English directly from your favorite LLM tools and IDEs

Real-time crypto whale intelligence MCP server with 54 tools across 14 blockchains. No auth required.

18 detection engines across crypto and US equities/ETFs return read-only market-risk verdicts — every one judged against realized outcomes in a public ledger, misses included.

Remote MCP server for prediction markets — search and compare live odds across Polymarket, Kalshi, and Limitless from Claude, ChatGPT, or Gemini. Six read-only tools, free tier available.

Graded trading signals & market analysis (FX, crypto, sports, prediction markets) with a public machine-graded track record. Free track-record tools; pay per call with x402 USDC or credit packs.

Covers Forex/FX · Precious Metals · Indices · US Stocks (NASDAQ/NYSE) · HK Stocks · A-shares/CN Stocks · Cryptocurrency through 13 MCP tools backed by a REST API.

Real-time and historical FX/crypto signal API for AI agents. Pay-per-call via x402 protocol on Base. No subscription, no API key. Correlation, regime, momentum, volatility across 10 instruments.

Market phase transition signals (Phi/Chi critical state detection) for HS300 and BTC. Free sensing and briefing endpoints. x402 payment protocol for advanced tools. Action signals by role.