MCP Jupiter

@MCP-Mirror

About MCP Jupiter

Mirror of

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "dcSpark_mcp-server-jupiter": {
      "command": "npx",
      "args": [
        "@mcp-dockmaster/mcp-server-jupiter"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP Jupiter?

MCP Jupiter is a Model Context Protocol (MCP) server that provides Claude with access to Jupiter’s swap API on the Solana blockchain. It enables Claude to get quotes, build swap transactions, and send swaps using natural language commands.

How to use MCP Jupiter?

Install the server, build it, and configure Claude Desktop by adding the server to its claude_desktop_config.json. After restarting Claude, you can ask it to get a quote, build a swap transaction, or send a swap transaction.

Key features of MCP Jupiter

jupiter_get_quote – get a quote for swapping tokens
jupiter_build_swap_transaction – build a swap transaction
jupiter_send_swap_transaction – send a swap transaction
Works with Claude Desktop application
Interacts directly with Jupiter’s Solana swap API

Use cases of MCP Jupiter

Ask Claude for a quote to swap tokens (e.g., 1 SOL to USDC)
Build a swap transaction from a previously obtained quote
Send the built swap transaction on the Solana blockchain

FAQ from MCP Jupiter

What are the prerequisites?

Node.js v16 or higher and the Claude Desktop application are required.

How do I configure Claude Desktop to use this server?

Add the server to the Claude Desktop configuration file (claude_desktop_config.json) with the appropriate command and arguments for your installation method (local, global, or npx).

Can I install the server globally?

Yes. You can install it globally with npm install -g @mcp-dockmaster/mcp-server-jupiter or use it directly with npx @mcp-dockmaster/mcp-server-jupiter.

How do I run the server locally?

Run node build/index.js from the project directory, or mcp-server-jupiter if installed globally, or npx @mcp-dockmaster/mcp-server-jupiter.

What can Claude do with this server?

Claude can get token swap quotes, build swap transactions, and send swap transactions on the Solana blockchain using Jupiter.

Frequently asked questions

What are the prerequisites?

Node.js v16 or higher and the Claude Desktop application are required.

How do I configure Claude Desktop to use this server?

Add the server to the Claude Desktop configuration file (`claude_desktop_config.json`) with the appropriate command and arguments for your installation method (local, global, or npx).

Can I install the server globally?

Yes. You can install it globally with `npm install -g @mcp-dockmaster/mcp-server-jupiter` or use it directly with `npx @mcp-dockmaster/mcp-server-jupiter`.

How do I run the server locally?

Run `node build/index.js` from the project directory, or `mcp-server-jupiter` if installed globally, or `npx @mcp-dockmaster/mcp-server-jupiter`.

What can Claude do with this server?

Claude can get token swap quotes, build swap transactions, and send swap transactions on the Solana blockchain using Jupiter.

Comments

Basic information

More Other MCP servers

MaxKB

1Panel-dev

🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

22.0K

DeepMark

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

MCP Registry

modelcontextprotocol

A community driven registry service for Model Context Protocol (MCP) servers.

7.0K

MCP Go 🚀

mark3labs

A Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.

8.9K

Peekaboo MCP – lightning-fast macOS screenshots for AI agents

steipete

Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.

4.8K