CCXT vs Yahoo Finance (narumiruna)
Two MCP servers from our finance ranking, compared on live data - updated nightly, never sponsored.
Bottom line · 2026-09-18
Yahoo Finance (narumiruna) records significantly more monthly package installs (11,080 vs 1,921); both are actively maintained, with commits inside the last month.
How they differ in kind
CCXT focuses on: A crypto trading API with more than 100 exchanges and prediction markets in JavaScript / TypeScript / Python / C / PHP / Go / Java / Rust. Yahoo Finance (narumiruna) focuses on: A Model Context Protocol (MCP) server that provides AI assistants with access to Yahoo Finance data via yfinance. Implementation languages differ (Rust vs Python).
What each one does
CCXT
A crypto trading API with more than 100 exchanges and prediction markets in JavaScript / TypeScript / Python / C / PHP / Go / Java / Rust. It runs locally over stdio via the published package.
From the project's README.
Yahoo Finance (narumiruna)
A Model Context Protocol (MCP) server that provides AI assistants with access to Yahoo Finance data via yfinance. Query stock information, financial news, sector rankings, and generate professional financial charts - all from your AI chat. Its 21 documented tools cover yfinance, holders, insider, ticker. It runs locally over stdio via the published package.
From the project's README.
14 signals, side by side
| Signal | CCXT | Yahoo Finance (narumiruna) |
|---|---|---|
| Monthly installs | 1,921 | 11,080 |
| GitHub stars | 44,030 | 195 |
| Last commit | 2026-09-18 | 2026-09-14 |
| Releases · last 90 days | 10+ | 6 |
| In the registry since | Sep 2026 | Jul 2026 |
| Registry versions | 1 | 2 |
| Documented tools | not extracted - see README | 21 |
| Env vars extracted | none extracted - see README | none extracted - see README |
| Runs | local (stdio) | local (stdio) |
| Endpoint auth | local only | local only |
| Maintenance | actively maintained | actively maintained |
| License | MIT | MIT |
| Language | Rust | Python |
| Category rank | #2 of 318 | #3 of 318 |
What their tools cover
Extracted from each project's README - the tools each server hands your agent. A missing list means the README doesn't document one, not that no tools exist.
CCXT no tool list in README
Yahoo Finance (narumiruna) 21 tools documented
major_holders- Aggregated breakdown where each row has an index label (e.g.…institutional_holders- Institutional investors; records typically include fields such as…mutualfund_holders- Mutual fund holders; records typically include fields similar to…insider_transactions- Recent insider trades; records typically include fields such as…insider_purchases- Six-month summary where each row describes a category (Purchases…insider_roster- Known insiders; records typically include fields such as Name…yfinance_get_ticker_info- Retrieve comprehensive stock data including company info…yfinance_get_analyst_price_targets- Fetch the current price and analyst consensus price targets for a…
+13 more on the full page
Which one, for what
Derived from the signals above, not hands-on testing.
Pick CCXT if…
- → release velocity matters - 10+ releases in 90 days vs 6
- → you prefer a Rust codebase to extend or audit
Pick Yahoo Finance (narumiruna) if…
- → you want the more widely installed option - 11,080 monthly installs vs 1,921
- → you prefer a Python codebase to extend or audit
Who's behind them
CCXT - ccxt: 1 MCP server tracked, 1 maintained, 44,030 combined stars.
Yahoo Finance (narumiruna) - narumiruna: 2 MCP servers tracked, 2 maintained, 201 combined stars. Full record.
Not sold on either?
The next-ranked finance servers we track:
Quick answers
Is CCXT better than Yahoo Finance (narumiruna)?
Package installs favor Yahoo Finance (narumiruna): 11,080 monthly installs to 1,921. CCXT still ranks #2 of 318 maintained finance servers. Data as of 2026-09-18; we haven't hands-on tested either.
Can I use CCXT and Yahoo Finance (narumiruna) together?
Yes - MCP clients accept multiple servers in one config, so you can enable both finance servers side by side. If their tools overlap, keep the one whose toolset fits to keep your agent's tool list lean.
Keep exploring: best finance servers · Rust servers · Python servers · all comparisons · every server
Methodology: package-usage signal = npm/PyPI installs (last month, platform APIs) · maintenance = commit recency + release cadence (GitHub) · tool lists and environment-variable names extracted from each project's README · endpoint auth from our own nightly probes. We haven't hand-tested these servers; everything here is data as of 2026-09-18.