Netmind Web3 MCP Server
Provides a comprehensive suite of Web3 tools for querying token addresses, news summaries, and real-time market data via CoinGecko. It also facilitates DeFi operations including token price tracking, pool information, and swap quotes through Sugar DeFi integration.
README
Netmind Web3 MCP Server
This is an MCP (Model Context Protocol) server that provides Web3 tools.
Components
Tools
Backend Tools:
query_token_addressList- Query token addresses by name or address (supports multiple values)query_reply_by_news_summary- Query news by Web3 entity name
CoinGecko Tools:
query_coingecko_market_data- Market data with 7-day historical chartsquery_coingecko_top_token_traders- Top token traders analysis (requires Analyst plan)query_coingecko_pool_trades- Past 24h trades by pool addressquery_coingecko_token_trades- Past 24h trades by token address (requires paid plan)
Sugar DeFi Tools:
- Token queries, price data, pool information, and swap quotes (8 tools)
Environment Variables
All environment variables should be configured in the .env file in the project root.
Required:
BACKEND_BASE_URL: The backend base URL (domain only, route path is appended in code).COINGECKO_API_KEY: CoinGecko Pro API Key (format: CG-xxxxx).SUGAR_PK: Private key for the Sugar service (required for Sugar tools).SUGAR_RPC_URI_8453: RPC URI for Base chain (required for Sugar tools).
Optional:
MCP_TRANSPORT: Transport mode - "stdio" or "sse" (default: sse).MCP_HOST: Server host for SSE transport (default: 127.0.0.1).MCP_PORT: Server port for SSE transport (default: 8000).
See env.example for all available configuration options.
Quick Start
-
Setup environment:
source .venv/bin/activate pip install -e . # or: uv pip install -e . cp env.example .env # Edit .env with your API keys -
Start server:
python -m netmind_web3_mcp.serverServer starts in SSE mode on
http://127.0.0.1:8000by default.
Usage
Basic usage:
# Start with SSE transport (default: 127.0.0.1:8000)
python -m netmind_web3_mcp.server
# Start with SSE transport on custom host and port
MCP_HOST=0.0.0.0 MCP_PORT=9000 python -m netmind_web3_mcp.server
# Start with stdio transport
MCP_TRANSPORT=stdio python -m netmind_web3_mcp.server
MCP Client Configuration
For stdio transport (local development):
{
"mcpServers": {
"netmind-web3-mcp": {
"env": {
"BACKEND_BASE_URL": "***",
"COINGECKO_API_KEY": "***",
"MCP_TRANSPORT": "stdio"
},
"command": "uvx",
"args": [
"git+https://github.com/protagolabs/netmind-web3-mcp.git"
]
}
}
}
For SSE transport (remote connections), connect to the SSE endpoint:
- Default:
http://127.0.0.1:8000/sse - Custom:
http://your-host:your-port/sse
Debugging with MCP Inspector
Access the built-in Inspector at http://127.0.0.1:8000/inspector after starting the server.
Alternative: Use mcp dev test/test_mcp_inspector.py (automatically starts server in background).
Testing
python test/test_local_stdio.py # stdio transport
python test/test_sse.py # SSE transport
See test/README.md for details.
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
E2B
Using MCP to run code via e2b.