Futures
Access hundreds of perpetual contracts
TradFi
Gold
One platform for global traditional assets
Options
Hot
Trade European-style vanilla options
Unified Account
Maximize your capital efficiency
Demo Trading
Introduction to Futures Trading
Learn the basics of futures trading
Futures Events
Join events to earn rewards
Demo Trading
Use virtual funds to practice risk-free trading
Launch
CandyDrop
Collect candies to earn airdrops
Launchpool
Quick staking, earn potential new tokens
HODLer Airdrop
Hold GT and get massive airdrops for free
Launchpad
Be early to the next big token project
Alpha Points
Trade on-chain assets and earn airdrops
Futures Points
Earn futures points and claim airdrop rewards
More
I set up my Claude Code and ended up with 12 MCPs running globally.
Each MCP's tool description is a persistent system prompt, which consumes context whether you use it or not.
After 14 days of call data, only about 10 calls in total for 6 MCPs over two weeks.
So I decided to cut down to 6.
After the reduction, I started thinking: which tools should use MCP, and which are enough with just CLI?
The advantage of MCP is its structured approach—Claude can see the parameter schema, call directly, and handle complex interactions (login states, long connections, multi-step operations) more reliably.
But the cost is the persistent context. Having 10 MCPs means dozens of tool descriptions always hanging around.
CLI doesn’t have this overhead. Commands only enter context when you run them, and disappear afterward.
My current approach: for tools that require Claude to actively discover and call (like memory systems, TG messages), keep MCP. For everything else that can be CLI-ified, do so.
Keep global MCPs controlled within 5-6, and load others on demand per project.