mcpField
W
Web3 MCP

Web3 MCP

Local
github.com/tumfFinance9Updated 80w ago

About Web3 MCP

Web3 MCP wraps the Ankr Advanced API in an MCP server for clients that need blockchain data across multiple networks. It covers NFT, token, and general chain queries.

Key features

  1. 01Wraps Ankr Advanced API endpoints
  2. 02Query NFT metadata and holders
  3. 03Retrieve blocks, logs, and transactions
  4. 04Check balances, prices, and token transfers
  5. 05Supports multiple blockchain networks

Use cases

  1. 01Find NFTs owned by a wallet
  2. 02Check token balances and prices
  3. 03Look up transactions by address or hash
  4. 04Retrieve blockchain statistics and logs

MCP support

It exposes Ankr Advanced API blockchain data through an MCP server, with tools for NFT, general query, and token data.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Web3 MCP

Tests codecov PyPI version License: MIT

An MCP server implementation wrapping Ankr Advanced API.

Overview

FastMCP is a Model Context Protocol (MCP) server that provides access to Ankr's Advanced API for blockchain data. It allows LLMs to interact with blockchain data across multiple chains including Ethereum, BSC, Polygon, Avalanche, and more.

MCP Client Setting

{
  "mcpServers": {
    "web3": {
      "command": "uvx",
      "args": [
        "web3-mcp"
      ],
      "env": {
        "ANKR_ENDPOINT": "https://rpc.ankr.com/...",
      }
    }
  }
}

Features

  • Complete wrapper for all Ankr Advanced API endpoints
  • NFT API: Get NFT metadata, holders, transfers, and ownership information
  • Query API: Access blockchain statistics, blocks, logs, and transaction data
  • Token API: Get token balances, prices, holders, and transfer history
  • Support for multiple blockchain networks

Installation

# Clone the repository
git clone https://github.com/tumf/web3-mcp.git
cd web3-mcp

# Install with uv
uv pip install -e .

Configuration

Set the following environment variables:

# Required
export ANKR_ENDPOINT="your_ankr_rpc_endpoint"

# Optional but recommended for authenticated requests
export ANKR_PRIVATE_KEY="your_private_key"

Usage

Running the server
from web3_mcp.server import init_server

# Initialize MCP server
mcp = init_server(
    name="Ankr MCP",
    endpoint="your_ankr_endpoint",  # Optional, defaults to ANKR_ENDPOINT env var
    private_key="your_private_key"  # Optional, defaults to ANKR_PRIVATE_KEY env var
)

# Run server
mcp.run()
Using with FastMCP CLI
# Set environment variables first
export ANKR_ENDPOINT="your_ankr_endpoint"
export ANKR_PRIVATE_KEY="your_private_key"

# Run the server
python -m web3_mcp

API Categories

NFT API
  • get_nfts_by_owner: Get NFTs owned by a wallet address
  • get_nft_metadata: Get metadata for a specific NFT
  • get_nft_holders: Get holders of a specific NFT collection
  • get_nft_transfers: Get transfer history for NFTs
Query API
  • get_blockchain_stats: Get blockchain statistics
  • get_blocks: Get blocks information
  • get_logs: Get blockchain logs
  • get_transactions_by_hash: Get transactions by hash
  • get_transactions_by_address: Get transactions by address
  • get_interactions: Get wallet interactions with contracts
Token API
  • get_account_balance: Get token balances for a wallet
  • get_currencies: Get available currencies
  • get_token_price: Get token price information
  • get_token_holders: Get token holders
  • get_token_holders_count: Get token holders count
  • get_token_transfers: Get token transfer history

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.