REI Crypto MCP Server - Beta
A FastMCP implementation of the in-house MCP servers used by Units of the Rei Network.
REI Crypto MCP Server - Beta
FastMCP implementation of the in-house MCP servers used by Units of the Rei Network. You can use them without providing API keys at app.reisearch.box or you can use them with other MCP clients deploying them yourself.
Everything is to be considered still in beta. Expect things to be added or changed with no warnings.
Current MCP servers:
- DefiLlama Pro API
- CoinGecko Pro API
- Arkham Intelligence API
- Elfa AI API
- Codex API
Codex at the moment is just used for searching a contract address from the name. Deeper implementation will come in the near future. Codex uses GraphQL for it's query system. Edit the query to hardcode some parameters in case you need stricter filtering.
Prerequisites
- Python 3.12
uvpackage manager- API keys for the services you plan to use
Installation
- Clone the repository:
git clone https://github.com/0xReisearch/crypto-mcp-beta
cd crypto-mcp-beta
- Install uv (if not already installed):
curl -LsSf https://astral.sh/uv/install.sh | sh
- Create and activate a virtual environment with uv:
uv venv
source .venv/bin/activate # On Unix/macOS
# or
.venv\Scripts\activate # On Windows
- Install dependencies from pyproject.toml:
uv pip install .
- Set up your environment variables:
cp .env_example .env
Edit .env with your API keys:
ARKHAM_API_KEY=<YOUR ARKHAM_API_KEY>
CG_API_KEY=<YOUR_CG_API_KEY>
DEFILLAMA_API_KEY=<YOUR_DEFILLAMA_API_KEY>
CODEX_API_KEY=<YOUR_CODEX_API_KEY>
ELFA_API_KEY=<YOUR_ELFA_API_KEY>
Running the Servers
You can run each server individually:
# Run DefiLlama server
uv run defillama_server.py
# Run CoinGecko server
uv run cg_server.py
# Run Arkham server
uv run arkham_server.py
# Run Codex server
uv run codex_server.py
# Run Elfa AI server
uv run elfa_server.py
Configuring Claude Desktop
To use these servers with Claude Desktop, you need to configure the claude_desktop_config.json file. This file is typically located in:
- Windows:
%APPDATA%/claude-desktop/claude_desktop_config.json - macOS:
~/Library/Application Support/claude-desktop/claude_desktop_config.json - Linux:
~/.config/claude-desktop/claude_desktop_config.json
Example configuration:
{
"mcpServers": {
"arkham": {
"command": "ssh",
"args": [
"user@your-host",
"cd /path/to/crypto_mcp && /path/to/uv run arkham_server.py"
]
},
"coingecko": {
"command": "ssh",
"args": [
"user@your-host",
"cd /path/to/crypto_mcp && /path/to/uv run cg_server.py"
]
},
"defillama": {
"command": "ssh",
"args": [
"user@your-host",
"cd /path/to/crypto_mcp && /path/to/uv run defillama_server.py"
]
},
"codex": {
"command": "ssh",
"args": [
"user@your-host",
"cd /path/to/crypto_mcp && /path/to/uv run codex_server.py"
]
},
"elfa": {
"command": "ssh",
"args": [
"user@your-host",
"cd /path/to/crypto_mcp && /path/to/uv run elfa_server.py"
]
}
}
}
Replace the following:
user@your-host: Your SSH username and host/path/to/crypto_mcp: The absolute path to where you cloned this repository/path/to/uv: The absolute path to your uv installation (usually in~/.local/bin/uvon Unix systems)
API Documentation
- DefiLlama API Documentation
- CoinGecko API Documentation
- Codex API Documentation
- Elfa AI Api Documentation - Contact Elfa directly for api access.
- Arkham Intelligence - You need to contact Arkham directly for api access.
Feedback
If you encounter any issues or have suggestions for improvements:
- For bug reports or feature requests, please open an issue in this repository
- For general feedback or questions, you can leave a comment in the repository discussions
Made with ❤️ by Rei Network
Related Servers
Bedrock Server Manager
Manage your Bedrock server with natural language commands using the Bedrock Server Manager API.
Unison MCP Server
An MCP server for the Unison language, allowing AI assistants to interact with the Unison Codebase Manager (UCM).
MCP Code Executor
Allows LLMs to execute Python code within a specified and configurable Python environment.
Remote MCP Server (Authless)
An example of a remote MCP server without authentication, deployable on Cloudflare Workers.
QA Sphere
Integration with QA Sphere test management system, enabling LLMs to discover, summarize, and interact with test cases directly from AI-powered IDEs
SpecBridge
Automatically generates MCP tools from OpenAPI specifications by scanning a folder for spec files. No configuration is needed and it supports authentication via environment variables.
Ai Notify MCP
Receive system notifications in your code editor when an AI response is complete.
Remote MCP Server (Authless)
An authentication-free, remote MCP server deployable on Cloudflare Workers or locally via npm.
Codebase MCP Server
An intelligent codebase search engine that transforms local codebases into a natural language queryable knowledge base.
Accordo MCP Server
Provides dynamic YAML-driven workflow guidance for AI coding agents with structured development workflows, progression control, and decision points.