📈 MemePortfolio MCP Server

MCP Server Name: MemePortfolio MCP

Category: DeFi / Solana / Meme Tokens / Portfolio Management

Status: Public tools – Private backend

Access: Pay-per-call via x402

Server URL: [https://mcp.memeportfolio.io/mcp]

Website: [https://MemePortfolio.io]

Twitter: [https://x.com/MemePortfolio1]

Blog: [https://blog.memeportfolio.io/blog/]

mcp-name: io.github.MemePortfolio/memeportfolio-mcp

📖 Description

The MemePortfolio MCP Server provides AI-powered tools to interact with MemePortfolio's Solana meme token portfolio engine.

Developers and AI agents can integrate these tools through the MCP protocol to build optimal Markowitz portfolios of Solana meme tokens and analyse existing wallet holdings - including token balances, prices, and risk metrics.

All tools follow the Model Context Protocol (MCP) and can be consumed via any MCP-compatible client.

⚙️ Available Tools

1. Create Markowitz Portfolio Tool

ID: create_markowitz_portfolio

Description: Creates an optimal Markowitz mean-variance portfolio of Solana meme tokens. The algorithm selects and weights tokens to maximise the Sharpe ratio, balancing expected return against volatility.

Use this when a user wants an optimised meme token portfolio built from quantitative analysis.

➡️ Example Use Cases:

• "Build me an optimal Solana meme token portfolio with 10 tokens."
• "What is the best allocation across meme tokens right now?"
• "Create a Markowitz portfolio for Solana meme coins."

Inputs:

Name	Type	Required	Default	Constraints
`number_of_tokens`	int	No	`10`	Min: 2, Max: 50

Outputs (JSON):

{
  "portfolio": [
    {
      "symbol": "string",             // token ticker symbol (e.g. "BONK")
      "chain": "string",              // blockchain network (e.g. "SOLANA")
      "weight": 0.0,                  // portfolio allocation weight as a percentage
      "annual_return": 0.0,           // annualised expected return (%)
      "annual_volatility": 0.0,       // annualised volatility (%)
      "sharpe_ratio": 0.0,            // Sharpe ratio
      "sortino_ratio": 0.0            // Sortino ratio
    }
  ],
  "portfolio_metrics": {
    "total_tokens": 0,                // number of tokens in portfolio
    "annual_return": 0.0,             // portfolio-level annualised return (%)
    "annual_volatility": 0.0,         // portfolio-level annualised volatility (%)
    "sharpe_ratio": 0.0,              // portfolio Sharpe ratio
    "sortino_ratio": 0.0,             // portfolio Sortino ratio
    "total_weight": 100.0             // sum of all weights (always 100)
  }
}

Error cases:

• `400 Bad Request` → invalid `number_of_tokens` value
• `500 Internal Server Error` → temporary downstream failure

2. Get Portfolio Tool

ID: get_portfolio

Description: Returns token balances, current prices, USD values, and risk metrics for a user's existing Solana meme token portfolio identified by wallet address.

Use this when a user wants to understand their current holdings and the risk/return profile of each position.

➡️ Example Use Cases:

• "What meme tokens do I hold and what are they worth?"
• "Show me the risk metrics for my Solana wallet."
• "Analyse the portfolio for wallet address ABC123..."

Inputs:

Name	Type	Required	Constraints
`wallet`	string	✅	Valid Solana public key (base58, 32–44 chars)

Outputs (JSON):

{
  "token_metrics": [
    {
      "symbol": "string",             // token ticker symbol (e.g. "BONK")
      "chain": "string",              // blockchain network (e.g. "SOLANA")
      "contractAddress": "string",    // token contract / mint address
      "balance": 0,                   // token balance held by wallet
      "price": 0.0,                   // current token price in USD
      "value": 0.0,                   // current USD value of holding
      "metrics": {
        "weight": 0.0,                // portfolio weight as a percentage
        "annual_return": 0.0,         // annualised expected return (%)
        "annual_volatility": 0.0,     // annualised volatility (%)
        "sharpe_ratio": 0.0,          // Sharpe ratio
        "sortino_ratio": 0.0          // Sortino ratio
      }
    }
  ],
  "portfolio_metrics": {
    "total_tokens": 0,                // number of distinct tokens held
    "annual_return": 0.0,             // portfolio-level annualised return (%)
    "annual_volatility": 0.0,         // portfolio-level annualised volatility (%)
    "sharpe_ratio": 0.0,              // portfolio Sharpe ratio
    "sortino_ratio": 0.0,             // portfolio Sortino ratio
    "total_weight": 100.0             // sum of all weights (always 100)
  }
}

Error cases:

• `400 Bad Request` → invalid or malformed `wallet` address
• `500 Internal Server Error` → temporary downstream failure

🧠 Example Client Usage

Node.js Example

import { MCPClient } from "mcp-client";

const client = new MCPClient("https://mcp.memeportfolio.io/mcp");

const result = await client.call("create_markowitz_portfolio", {
  number_of_tokens: 10
});

console.log(result);

Python Example

from mcp_client import MCPClient

client = MCPClient("https://mcp.memeportfolio.io/mcp")

res = client.call("get_portfolio", {
  "wallet": "YourSolanaPublicKeyHere"
})
print(res)

Service Configuration:

{
  "mcpServers": {
    "memeportfolio-mcp": {
      "type": "http",
      "url": "https://mcp.memeportfolio.io/mcp",
      "description": "The MemePortfolio MCP Server provides tools to build optimal Markowitz portfolios of Solana meme tokens and analyse existing wallet holdings.",
      "auth": {
        "type": "x402"
      }
    }
  }
}

🔌 Integration Notes

✅ Compatible with MCP clients across Node.js, Python, and browser-based environments
🔁 Uses Streamable HTTP transport (POST /mcp) per the MCP specification
📐 JSON schemas conform to the MCP specification
🚦 Rate limits may apply depending on usage tier
💳 x402 payments - pay-per-call via the x402 protocol; compatible x402 clients handle payment automatically on HTTP 402 responses

Claude Code (CLI) Configuration

Use the Claude CLI to register the MCP server via Streamable HTTP transport:

claude mcp add --transport http memeportfolio-mcp-server https://mcp.memeportfolio.io/mcp

📚 Documentation: https://code.claude.com/docs/en/mcp

ChatGPT Connector Configuration

Available in ChatGPT environments that support Connectors / MCP (Developer Mode).

Steps

Open ChatGPT Settings
Navigate to Apps / Connectors
Click Add Connector
Enter the integration name and URL below
Save the configuration

Integration Details

Name

MemePortfolio MCP Server

Integration URL

https://mcp.memeportfolio.io/mcp

Claude Web & Claude Desktop Configuration

Steps

Open Claude Web or Claude Desktop
Go to Settings → Integrations
Click Add integration
Enter the name and URL below
Click Add to complete setup

Integration Details

Name

MemePortfolio MCP Server

Integration URL

https://mcp.memeportfolio.io/mcp

📚 Documentation: https://platform.claude.com/docs/en/agents-and-tools/remote-mcp-servers

Cursor Configuration

Add the MCP server to your Cursor configuration file (e.g. mcp.json):

{
  "mcpServers": {
    "memeportfolio-mcp-server": {
      "url": "https://mcp.memeportfolio.io/mcp",
      "transport": "http"
    }
  }
}

📚 Documentation: https://cursor.com/docs/context/mcp

🤖 Claude Code Subagents

This repository includes 2 ready-to-use Claude Code subagents in .claude/agents/ - specialist agents that handle Solana meme token portfolio tasks out of the box.

Agent	Purpose
`memeportfolio-portfolio-builder`	Builds an optimal Markowitz portfolio of Solana meme tokens
`memeportfolio-portfolio-analyzer`	Analyses existing wallet meme token holdings

Setup

Step 1 - Connect the MCP server

claude mcp add --transport http memeportfolio-mcp-server https://mcp.memeportfolio.io/mcp

For Cursor / Windsurf, add to mcp.json:

{
  "mcpServers": {
    "memeportfolio-mcp-server": {
      "url": "https://mcp.memeportfolio.io/mcp",
      "transport": "http"
    }
  }
}

Step 2 - Copy the agent files

git clone https://github.com/MemePortfolio/memeportfolio-mcp.git
cp -r memeportfolio-mcp/.claude/agents/ your-project/.claude/agents/

Running Locally

Prerequisites: Node.js 18+

Clone the repo and install dependencies:

npm install

Run in development mode:

npm run dev

Build for production:

npm run build

Run the built server:

node dist/index.js

Test with MCP Inspector:

npx @modelcontextprotocol/inspector node dist/index.js

🔒 Access Policy

The MCP server uses x402 pay-per-call access - no subscription or API key required. Any x402-compatible MCP client will handle payment automatically when the server returns HTTP 402.

🤝 A2A Protocol (Agent-to-Agent)

The server implements Google's A2A protocol for direct agent-to-agent interoperability - no MCP client required.

Agent card discovery:

GET https://mcp.memeportfolio.io/.well-known/agent.json

Endpoints:

Method	Path	Description
`GET`	`/.well-known/agent.json`	Agent card - capabilities, skills, and provider metadata
`POST`	`/a2a/tasks/send`	Submit a task, receive the completed result in one response
`POST`	`/a2a/tasks/sendSubscribe`	Submit a task, receive SSE state-transition events
`GET`	`/a2a/tasks/{task_id}`	Poll task state by ID

Skills:

Skill ID	Maps to	Required input	Optional input
`create-markowitz-portfolio`	`create_markowitz_portfolio`	-	`number_of_tokens` (int, 2-50)
`get-portfolio`	`get_portfolio`	`wallet` (Solana public key)	-

Example task request:

{
  "id": "task-001",
  "skillId": "create-markowitz-portfolio",
  "message": {
    "parts": [{
      "type": "data",
      "data": { "number_of_tokens": 10 }
    }]
  }
}

Both skills complete synchronously. The sendSubscribe endpoint emits submitted → working → completed events.

🔗 Framework Integrations

Fetch.ai / Agentverse Integration - connect MemePortfolio tools to uAgents and DeltaV
ElizaOS Integration - add portfolio tools to any Eliza character

📖 Further Reading

AGENTS.md - index of both Claude Code subagents with triggers, tools, and output formats
SKILL.md - full skill definition for Claude Code and ClawHub
references/tools-create-markowitz-portfolio.md - full create_markowitz_portfolio schema and code examples
references/tools-get-portfolio.md - full get_portfolio schema and code examples

🧾 License

MIT (for client examples). Server implementation and backend logic are proprietary and remain private.

Name		Name	Last commit message	Last commit date
.claude/agents		.claude/agents
agents		agents
assets		assets
eliza/characters		eliza/characters
references		references
.gitignore		.gitignore
AGENTS.md		AGENTS.md
CLAUDE.md		CLAUDE.md
LICENSE		LICENSE
OPENAI-REGISTRY.md		OPENAI-REGISTRY.md
README.md		README.md
SKILL.md		SKILL.md
glama.json		glama.json
llms.txt		llms.txt
memeportfolio-eliza-integration.md		memeportfolio-eliza-integration.md
memeportfolio-fetchai-integration.md		memeportfolio-fetchai-integration.md
readme.md		readme.md
server.json		server.json

Navigation Menu

Repository files navigation

📈 MemePortfolio MCP Server

📖 Description

⚙️ Available Tools

1. Create Markowitz Portfolio Tool

2. Get Portfolio Tool

🧠 Example Client Usage

Node.js Example

Python Example

🔌 Integration Notes

Claude Code (CLI) Configuration

ChatGPT Connector Configuration

Steps

Integration Details

Claude Web & Claude Desktop Configuration

Steps

Integration Details

Cursor Configuration

🤖 Claude Code Subagents

Setup

Running Locally

🔒 Access Policy

🤝 A2A Protocol (Agent-to-Agent)

🔗 Framework Integrations

📖 Further Reading

🧾 License

About

Releases

Packages

Contributors

Latest commit

History

Folders and files

Repository files navigation

📈 MemePortfolio MCP Server

📖 Description

⚙️ Available Tools

1. Create Markowitz Portfolio Tool

2. Get Portfolio Tool

🧠 Example Client Usage

Node.js Example

Python Example

🔌 Integration Notes

Claude Code (CLI) Configuration

ChatGPT Connector Configuration

Steps

Integration Details

Claude Web & Claude Desktop Configuration

Steps

Integration Details

Cursor Configuration

🤖 Claude Code Subagents

Setup

Running Locally

🔒 Access Policy

🤝 A2A Protocol (Agent-to-Agent)

🔗 Framework Integrations

📖 Further Reading

🧾 License

About

Resources

Stars

Watchers

Forks

Releases

Packages

Contributors