Apollo_BlockChain_Explorer_Hub
A powerful, AI-driven blockchain explorer powered by specialized Pydantic agents. This project uses a FastMCP server to expose tools for querying chain data, analyzing accounts, and checking transaction statuses directly within the Claude Desktop app, including complex cross-agent analytical workflows.
claude mcp add --transport stdio anirudhmsu-apollo_blockchain_explorer_hub python -m src.server \ --env MCP_HOST="127.0.0.1" \ --env MCP_PORT="4000" \ --env SUPABASE_KEY="your-anon-key" \ --env SUPABASE_URL="https://your-project.supabase.co" \ --env WEB3_PROVIDER_URL="https://eth-mainnet.g.alchemy.com/v2/YOUR_API_KEY"
How to use
Apollo Blockchain Explorer Hub is a FastMCP-based server that exposes four specialized AI agents for blockchain analytics: Chain Agent for real-time blockchain data, Account Agent for address balance analysis (ETH and ERC-20), Transaction Agent for monitoring transaction status and fees, and Analytics Agent for advanced analytics and holder insights. These agents can be orchestrated through cross-agent workflows, enabling natural-language queries via Claude Desktop. Users can ask questions like latest block details, address balances, transaction statuses, or holder distributions, and the hub will coordinate the appropriate agents to produce a cohesive answer. The system stores analytics results in Supabase, enabling persistent analytics history and easy retrieval for further analysis or reporting.
How to install
Prerequisites:
- Python 3.8+ and a working Python virtual environment
- Node.js (for Claude Desktop integration, if you plan to use it)
- Alchemy (or another Web3 provider) API key
- Supabase account and project
- Claude Desktop (optional for Claude integration)
Step 1: Create a Python virtual environment
# Create virtual environment
python -m venv venv
# Activate virtual environment
# macOS/Linux
source venv/bin/activate
# Windows
venv\Scripts\activate
Step 2: Install dependencies
pip install -r requirements.txt
Step 3: Configure environment Create a .env file (or set environment variables) with required values:
WEB3_PROVIDER_URL=https://eth-mainnet.g.alchemy.com/v2/YOUR_API_KEY
SUPABASE_URL=https://your-project.supabase.co
SUPABASE_KEY=your-anon-key
MCP_HOST=127.0.0.1
MCP_PORT=4000
Step 4: Run the MCP server
# Ensure virtual environment is activated
# macOS/Linux
source venv/bin/activate
# Windows
venv\Scripts\activate
# Start the Apollo MCP server
python -m src.server
Step 5: Optional Claude Desktop integration
- Install Claude Desktop and enable Developer Mode as described in the README
- Install MCP server integration via FastMCP if desired:
fastmcp install claude-desktop src/server.py
Step 6: Verify Open Claude Desktop and look for Apollo Blockchain Explorer tools, or connect via MCP host and port (127.0.0.1:4000 by default).
Additional notes
Tips and common considerations:
- Ensure your Web3 provider URL is valid and not rate-limited by your provider.
- Supabase credentials must be kept secure; use environment variables or secret managers in production.
- If Claude Desktop cannot connect, verify the MCP_HOST/MCP_PORT configuration, ensure the Python process is running, and confirm the Python path used by Claude Desktop is correct in the manual config example.
- The Analytics store in Supabase uses a dedicated analytics table; make sure migrations or table creation steps are performed as shown in the README.
- Cross-Agent workflows enable complex queries; you can combine real-time data retrieval with historical analytics to answer sophisticated questions (e.g., “Show top 10 holders of USDC with recent transfer activity”).
- The server defaults to 127.0.0.1:4000; if you need external access, adjust MCP_HOST and networking accordingly and secure the endpoint.
Related MCP Servers
okta
The Okta MCP Server is a groundbreaking tool built by the team at Fctr that enables AI models to interact directly with your Okta environment using the Model Context Protocol (MCP). Built specifically for IAM engineers, security teams, and Okta administrators, it implements the MCP specification to help work with Okta enitities
ChatSpatial
🧬 Analyze spatial transcriptomics data through natural language conversation. Stop writing code, start having conversations with your data. MCP server for Claude Code and Codex.
linkedin_mcp
A powerful Model Context Protocol server for LinkedIn interactions that enables AI assistants to search for jobs, generate resumes and cover letters, and manage job applications programmatically.
Omnispindle
A comprehensive MCP-based todo management system, that serves as a central nervous system for Madness Interactive, a multi-project task coordination workshop.
TexMCP
A small FastMCP-based Microservice that renders LaTeX to PDF. The server exposes MCP tools to render raw LaTeX or templates and produces artifacts
Taskx-nano
A python library built to execute tasks with natural language