Zerion MCP Server

Zerion MCP Server

Enables AI assistants to access cryptocurrency portfolio management, DeFi positions, NFTs, and market data through the Zerion API. Automatically exposes all Zerion API endpoints as MCP tools for comprehensive crypto asset management.

Category
Visit Server

README

Zerion MCP Server

A production-ready Model Context Protocol (MCP) server that provides AI assistants with access to the Zerion API for cryptocurrency portfolio management, DeFi positions, NFTs, and market data.

Features

  • 🔌 Auto-generated Tools: Automatically exposes Zerion API endpoints as MCP tools via OpenAPI specification
  • ⚙️ Flexible Configuration: YAML config files with environment variable overrides
  • 📝 Structured Logging: JSON and text formats with sensitive data redaction
  • 🛡️ Robust Error Handling: Custom exceptions with detailed context and troubleshooting hints
  • Comprehensive Tests: Unit and integration tests with pytest
  • 🚀 Async HTTP: Non-blocking API calls with httpx

Available Functions

  • getChainById: Returns a chain by its unique chain identifier.
  • getFungibleById: Returns a fungible asset by its unique identifier.
  • getFungibleChart: Returns the chart for a fungible asset for a selected period.
  • getNFTById: Returns a single NFT by its unique identifier.
  • getWalletChart: Returns a portfolio balance chart for a wallet.
  • getWalletNftPortfolio: Returns the NFT portfolio overview of a web3 wallet.
  • getWalletPNL: Returns the Profit and Loss (PnL) details of a web3 wallet.
  • getWalletPortfolio: Returns the portfolio overview of a web3 wallet.
  • listChains: Returns a list of all chains supported by Zerion.
  • listFungibles: Returns a paginated list of fungible assets supported by Zerion.
  • listGasPrices: Provides real-time information on the current gas prices across all supported blockchain networks.
  • listNFTs: Returns a list of NFTs by using different parameters.
  • listWalletNFTCollections: Returns a list of the NFT collections held by a specific wallet.
  • listWalletNFTPositions: Returns a list of the NFT positions held by a specific wallet.
  • listWalletPositions: Returns a list of wallet positions.
  • listWalletTransactions: Returns a list of transactions associated with the wallet.
  • swapFungibles: Provides a list of fungibles available for bridge exchange.
  • swapOffers: Provides a comprehensive overview of relevant trades and bridge exchanges.

Requirements

Installation

From Source

# Clone the repository
git clone https://github.com/SAK1337/myzerionmcp.git
cd myzerionmcp

# Install the package
pip install -e .

# For development (includes testing dependencies)
pip install -e ".[dev]"

From PyPI (when published)

pip install zerion-mcp-server

Quick Start

1. Set up your API key

export ZERION_API_KEY="Bearer your-api-key-here"

2. Run the server

zerion-mcp-server

3. Connect with an MCP client

The server will start and listen for MCP protocol connections. You can connect it to AI assistants like Claude Desktop.

Claude Desktop Configuration

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "zerion": {
      "command": "zerion-mcp-server",
      "env": {
        "ZERION_API_KEY": "Bearer your-api-key-here"
      }
    }
  }
}

Configuration

Configuration File

Create a config.yaml file in your working directory:

# Server configuration
name: "Zerion API"
base_url: "https://api.zerion.io"
oas_url: "https://raw.githubusercontent.com/smart-mcp-proxy/zerion-mcp-server/main/zerion_mcp_server/openapi_zerion.yaml"

# API authentication
api_key: "${ZERION_API_KEY}"  # Environment variable substitution

# Logging configuration
logging:
  level: "INFO"      # DEBUG, INFO, WARN, ERROR
  format: "text"     # text or json

See config.example.yaml for a complete example.

Environment Variables

Environment variables override config file values:

Variable Description Default
ZERION_API_KEY Zerion API key (required) -
ZERION_BASE_URL Zerion API base URL https://api.zerion.io
ZERION_OAS_URL OpenAPI spec URL GitHub raw URL
CONFIG_PATH Path to config.yaml ./config.yaml
LOG_LEVEL Logging level INFO
LOG_FORMAT Logging format (text/json) text

Usage Examples

Once connected to an MCP client (like Claude), you can query Zerion data:

Portfolio Balance

Get the portfolio balance for wallet 0x1234...

The server exposes tools like getWalletChart, getWalletPositions, etc.

DeFi Positions

Show me the DeFi positions for address 0xabcd...

NFT Collections

List NFTs owned by 0x5678...

All Zerion API endpoints are automatically available as MCP tools. See the Zerion API documentation for available operations.

Development

Setup Development Environment

# Clone and install with dev dependencies
git clone https://github.com/SAK1337/myzerionmcp.git
cd myzerionmcp
pip install -e ".[dev]"

# Set up API key
export ZERION_API_KEY="Bearer your-test-key"

Running Tests

# Run all tests
pytest

# Run with coverage
pytest --cov=zerion_mcp_server --cov-report=html

# Run specific test file
pytest tests/test_config.py

# Run with verbose output
pytest -v

Code Quality

# Type checking (if mypy is installed)
mypy zerion_mcp_server

# Linting (if ruff is installed)
ruff check zerion_mcp_server

Troubleshooting

Common Issues

"Configuration error: Missing required configuration: api_key"

Solution: Set the ZERION_API_KEY environment variable:

export ZERION_API_KEY="Bearer your-api-key-here"

"Timeout loading OpenAPI specification"

Solution: Check your internet connection. The server needs to download the OpenAPI spec from GitHub.

"Unauthorized: Invalid or missing API key"

Solution: Verify your API key is correct and includes the "Bearer " prefix:

export ZERION_API_KEY="Bearer your-actual-key"

"Rate limit exceeded"

Solution: Wait for the rate limit window to reset. Check the error message for retry_after_sec value.

Debug Mode

Enable debug logging for detailed information:

export LOG_LEVEL="DEBUG"
zerion-mcp-server

Or in config.yaml:

logging:
  level: "DEBUG"
  format: "json"  # Structured logs for analysis

Log Interpretation

  • INFO: Normal operation (startup, requests)
  • WARN: Potential issues (slow operations)
  • ERROR: Failures (API errors, network issues)
  • DEBUG: Detailed traces (request/response bodies)

Architecture

┌─────────────────┐
│   MCP Client    │ (e.g., Claude Desktop)
│  (AI Assistant) │
└────────┬────────┘
         │ MCP Protocol
         │
┌────────▼────────┐
│  FastMCP Server │
│                 │
│  ┌───────────┐  │
│  │ Config    │  │ (YAML + Env)
│  │ Manager   │  │
│  └───────────┘  │
│                 │
│  ┌───────────┐  │
│  │  Logger   │  │ (Structured)
│  └───────────┘  │
│                 │
│  ┌───────────┐  │
│  │  Error    │  │ (Custom Exceptions)
│  │  Handler  │  │
│  └───────────┘  │
│                 │
│  ┌───────────┐  │
│  │ HTTP      │  │ (httpx AsyncClient)
│  │ Client    │  │
│  └─────┬─────┘  │
└────────┼────────┘
         │
         │ HTTPS
         │
┌────────▼────────┐
│   Zerion API    │
│                 │
│  - Portfolios   │
│  - DeFi         │
│  - NFTs         │
│  - Transactions │
└─────────────────┘

Tech Stack

  • Python 3.11+: Core language
  • FastMCP: MCP server framework with OpenAPI integration
  • httpx: Async HTTP client
  • PyYAML: Configuration parsing
  • pytest: Testing framework

Contributing

Contributions are welcome! Please follow these guidelines:

  1. Fork the repository
  2. Create a feature branch: git checkout -b feature/your-feature
  3. Write tests for your changes
  4. Ensure tests pass: pytest
  5. Submit a pull request

Development Workflow

  • Follow PEP 8 style guidelines
  • Add type hints to function signatures
  • Write docstrings for modules and functions
  • Update tests for any code changes
  • Keep commits focused and atomic

License

MIT License - see LICENSE file for details

Support

Changelog

See CHANGELOG.md for version history and changes

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured