
This connects Claude to Twelve Data's financial market APIs through the Pipeworx gateway, giving you programmatic access to time series data, real-time quotes, dividends, stock splits, and earnings across stocks, ETFs, forex, and crypto. Rather than calling individual tools, you can use ask_pipeworx to query in plain English and let the gateway route to the right endpoint. It's hosted remotely over streamable HTTP, so no local setup required. Reach for this when you need market data in conversational workflows without managing API keys or parsing responses yourself. Part of Pipeworx's larger gateway that bundles 250+ data sources under one MCP interface.
Twelve Data MCP — stock, ETF, forex, crypto data. Free 800 req/day.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
PLATFORM_TWELVEDATA_KEY. BYO: ?_apiKey=….time_series(symbol, interval, exchange?, mic_code?, country?, type?, outputsize?, prepost?, dp?, order?, timezone?, date?, start_date?, end_date?, previous_close?, format?, delimiter?) — OHLC time seriesquote(symbol, interval?, exchange?, country?, format?, dp?, prepost?, timezone?, eod?) — quote snapshotprice(symbol, format?, prepost?) — latest priceeod(symbol, exchange?, mic_code?, country?, type?, prepost?, dp?, format?) — end-of-day quoteexchange_rate(symbol, format?, dp?, timezone?) — forex rate (e.g. EUR/USD)currency_conversion(symbol, amount, format?, dp?) — FX conversionstocks(symbol?, exchange?, mic_code?, country?, type?, format?) — stock symbolsforex_pairs(symbol?, currency_base?, currency_quote?, format?) — forex pairscryptocurrencies(symbol?, exchange?, currency_base?, currency_quote?, format?) — crypto symbolsetfs(symbol?, exchange?, country?, format?) — ETF symbolsindices(symbol?, country?, format?) — index symbolsearnings(symbol, exchange?, country?, mic_code?, type?, period?, outputsize?, format?, dp?, start_date?, end_date?) — earnings calendarearnings_calendar(start_date?, end_date?, country?, format?, dp?) — broad earnings calendardividends(symbol, exchange?, country?, mic_code?, range?, start_date?, end_date?) — dividendssplits(symbol, exchange?, country?, mic_code?, range?, start_date?, end_date?) — splitsprofile(symbol, exchange?, country?, mic_code?) — company profilehttps://api.twelvedata.com
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"twelvedata": {
"url": "https://gateway.pipeworx.io/twelvedata/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/twelvedata/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Twelvedata data" })
The gateway picks the right tool and fills the arguments automatically.
MIT