This server lets Claude interact with Jupiter's Portfolio and Price APIs to query Solana wallet positions and real-time token prices.
Get portfolio positions: Retrieve a wallet's full portfolio including balances, staking, liquidity pools, farming, vaults, and lending positions, optionally filtered by DeFi platforms.
Get staked JUP info: View how much JUP is staked for a wallet and any unstaking positions.
List supported platforms: See all DeFi platforms integrated with Jupiter's portfolio tracking.
Get token prices: Fetch current USD prices, 24h price changes, and token decimals for one or more token mint addresses.
Provides tools to access Jupiter's Portfolio API and Price API on Solana, enabling viewing portfolio positions, staked JUP tokens, and real-time token prices.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Jupiter MCP Server What's the current price of SOL and USDC?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This repository contains a Model Context Protocol (MCP) server that provides Claude with access to Jupiter's Portfolio API and Price API. The server enables Claude to view portfolio positions, track staked JUP tokens, and get real-time token prices on the Solana blockchain.
The MCP server exposes several tools to Claude:
jupiter_get_positions: Get portfolio positions including wallet balances, staked positions, liquidity pools, farming, vaults, lending, and more
jupiter_get_staked_jup: Get information about staked JUP tokens and unstaking positions
jupiter_get_platforms: Get a list of all DeFi platforms integrated with Jupiter's portfolio tracking
jupiter_get_price: Get current prices for one or more tokens, including USD price, 24h price change, and token decimals
Related MCP server: Wealthfolio MCP Server
This server uses Jupiter APIs:
Portfolio API v1 (https://api.jup.ag/portfolio/v1) for portfolio tracking and analytics
Price API v3 (https://api.jup.ag/price/v3) for real-time token pricing
Both APIs require an API key from Jupiter Portal.
Node.js (v16 or higher)
Claude Desktop application
Jupiter API key - Get yours at https://portal.jup.ag/
# Install globally
npm install -g jupiter-mcp-server
# Or use with npx
npx jupiter-mcp-serverClone this repository:
git clone https://github.com/quanghuynguyen1902/jupiter-mcp-server.git
cd jupiter-mcp-serverInstall dependencies:
npm ciBuild the project:
npm run buildInstall globally (optional):
npm install -g ./To configure Claude Desktop to use this MCP server:
Open Claude Desktop
Navigate to the Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\\Claude\\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
Add the MCP server configuration:
{
"mcpServers": {
"jupiter-mcp-server": {
"command": "npx",
"args": ["jupiter-mcp-server"],
"env": {
"JUPITER_API_KEY": "your_jupiter_api_key_from_portal"
}
}
}
}If you've installed from source and want to run the local version, use:
{
"mcpServers": {
"jupiter-mcp-server": {
"command": "node",
"args": [
"/path/to/your/jupiter-mcp-server/build/index.js"
],
"env": {
"JUPITER_API_KEY": "your_jupiter_api_key_from_portal"
}
}
}
}JUPITER_API_KEY (required): Your Jupiter API key from https://portal.jup.ag/
If you're running the server directly (not through Claude Desktop), you can create a .env file in the root directory:
JUPITER_API_KEY=your_jupiter_api_key_from_portal# If installed globally
jupiter-mcp-server
# If installed from source
node build/index.js
# Using npx
npx jupiter-mcp-serverOnce configured, restart Claude Desktop. Claude will now have access to Jupiter portfolio and price tools. You can ask Claude to:
View portfolio positions:
Show me the portfolio for address YOUR_WALLET_ADDRESSCheck staked JUP:
How much JUP is staked for address YOUR_WALLET_ADDRESS?List available platforms:
What platforms are supported for portfolio tracking?Get token prices:
What's the current price of SOL and USDC?Get multiple token prices:
Get prices for these tokens: So11111111111111111111111111111111111111112,EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1vIf you encounter 401 Unauthorized errors:
Verify your JUPITER_API_KEY is correctly set in the environment variables
Ensure your API key is valid - you can get a new one from https://portal.jup.ag/
Check that the API key doesn't have any extra spaces or quotes around it
To add new tools to the MCP server:
Define the tool in src/tools.ts
Create a handler function in the appropriate handler file
Add the handler to the handlers object in src/tools.ts
npm run buildnpm testMake sure you're logged in to npm:
npm loginThen publish the package:
npm publishTo publish a new version, first update the version in package.json:
npm version patch # or minor, or major
npm publishMIT
If Jupiter MCP Server is useful to you, consider sponsoring its development.
Your support helps maintain compatibility with Jupiter APIs, add new MCP tools, and improve the documentation.
Get a list of all DeFi platforms integrated with Jupiter's portfolio tracking system
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It does not mention return format, pagination, rate limits, or any other behavioral details. As a read-only list operation, the behavior is fairly straightforward, but the description fails to provide any additional context beyond the action itself.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no unnecessary words. It is front-loaded with the action and resource, making it easy to scan. This is exemplary conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (no input schema, no output schema), the description is essentially complete. It tells the agent what the tool returns. However, it does not note that the returned platform list might be used as inputs to other Jupiter tools, which could be a useful contextual hint, but it is not essential for using the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, and the schema coverage is trivially 100%. The baseline for 0 parameters is 4, and the description does not need to add parameter details. It correctly focuses on the output rather than input.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: retrieving a list of all DeFi platforms integrated with Jupiter's portfolio tracking system. It uses a specific verb ('Get a list') and a specific resource ('DeFi platforms'), which distinguishes it from sibling tools like jupiter_get_positions, jupiter_get_staked_jup, and jupiter_get_price.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool should be used when the agent needs to know which DeFi platforms are supported, but it does not explicitly state when to use it versus alternatives. There is no mention of exclusions or prerequisites, but the simple nature of the tool makes the implied usage acceptable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get portfolio positions for a Solana wallet address including wallet balances, staked positions, liquidity pools, farming, vaults, lending, and more
| Name | Required | Description | Default |
|---|---|---|---|
| address | Yes | Solana wallet address to query | |
| platforms | No | Optional comma-separated list of platform IDs to filter results (e.g., 'jupiter-exchange,jupiter-governance') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It reveals that the tool returns a broad set of position types, which is useful, but it doesn't disclose behaviors like default filtering, pagination, rate limits, or how errors are handled. The phrase 'and more' adds ambiguity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that front-loads the action and resource, then lists specific examples. Every word contributes value, with no redundant filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (aggregating multiple DeFi position types) and lack of output schema, the description provides a good overview but leaves gaps: no return format, no usage conditions, and no differentiation from siblings. It is adequate but not fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so both parameters are already documented. The description adds no extra semantics beyond what is in the schema, so the baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with a specific verb ('Get') and resource ('portfolio positions'), and enumerates the types of positions covered (wallet balances, staked positions, liquidity pools, etc.). This differentiates it from siblings like jupiter_get_staked_jup which is narrower in scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no explicit guidance on when to use this tool versus alternatives. For example, it doesn't mention that jupiter_get_staked_jup should be used if only staked JUP positions are needed. The description only states what the tool does, not the context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get current prices for one or more tokens on Jupiter, including USD price, 24h price change, and token decimals
| Name | Required | Description | Default |
|---|---|---|---|
| ids | Yes | Comma-separated list of token mint addresses (e.g., 'So11111111111111111111111111111111111111112,EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the transparency burden. It discloses the key return fields (USD price, 24h price change, token decimals) but does not mention potential behaviors like data freshness, caching, rate limits, or error cases. This is a moderate level of transparency for a simple read-only price tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that states the action, target, and key outputs without any filler or redundant detail. Every word contributes to understanding the tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read-only price lookup with no output schema, the description provides enough information about the tool's purpose and outputs to set expectations. It does not discuss error behavior or integration context, but the simplicity of the tool and the explicit output fields make the description reasonably complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema fully documents the only parameter 'ids' with a clear description and example, giving 100% schema coverage. The description does not add extra parameter-level semantics beyond what the schema already provides, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses the specific verb "Get" with a clear resource: "current prices for one or more tokens on Jupiter." It also enumerates included outputs (USD price, 24h change, token decimals), which distinguishes it from sibling tools that cover positions, staked JUP, and platforms.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies it is the tool for checking token prices by naming the resource and outputs, but it does not explicitly state when to use it versus siblings or provide any exclusions. Since the siblings address clearly different domains, the usage context is fairly evident.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get staked JUP tokens information for a Solana wallet address, including amount staked and unstaking positions
| Name | Required | Description | Default |
|---|---|---|---|
| address | Yes | Solana wallet address to query |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It clearly signals a read-only operation via the verb 'Get' and describes the return content (amount staked and unstaking positions). While it does not discuss rate limits or errors, the simple getter behavior is adequately disclosed for its purpose.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that front-loads the core action and resource, with no superfluous words. It efficiently conveys the tool's scope and output highlights.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one parameter, no output schema, no nested objects), the description is largely complete. It states the purpose and the main return fields. Minor gaps like return format or error conditions are acceptable for such a straightforward getter.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description repeats the schema's 'Solana wallet address' phrasing and adds no additional meaning, such as format or constraints. It otherwise does not compensate beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb (Get), the resource (staked JUP tokens information), and the scope (for a Solana wallet address). It also lists specific content (amount staked and unstaking positions), which distinctly separates it from sibling tools like get_positions, get_platforms, and get_price.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use the tool by explicitly naming the target resource (staked JUP), but it does not provide any explicit guidance on alternatives or exclusions. There is no mention of when to prefer this over jupiter_get_positions or other siblings, leaving usage to be inferred from the purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.4.0jupiter_get_platformsjupiter_get_positionsjupiter_get_pricejupiter_get_staked_jupScored across 4 tools
Tools are mostly distinct, but jupiter_get_positions includes staked positions while jupiter_get_staked_jup specifically covers staking, creating potential overlap. Descriptions help clarify the difference.
All tools follow the identical jupiter_get_ prefix with a clear noun suffix (positions, staked_jup, platforms, price). This is a perfectly consistent verb_noun pattern.
Four tools is well within the ideal range for a focused portfolio and price server. Each tool covers a distinct area, and the count feels neither sparse nor bloated.
The set covers core portfolio positions, staking details, platform listings, and prices. It lacks features like transaction history or swap execution, but that may not be the server's intended scope.
Jupiter - 4 tools for swap quotes, liquidity pools, and trading data
Connect your portfolio to Claude, ChatGPT, or Codex to analyze it and make smarter investments.
Solana tools over MCP: Jupiter swaps, SPL tokens, Metaplex NFTs, SNS domains, network stats.
Solana Jupiter quotes and package preflight for AI agents. Free sample. Paid x402 on Solana USDC.