CryptoToolBox MCP Server
A free, zero-dependency Model Context Protocol (MCP) server for AI agents providing Web3/crypto toolkit (balances, ENS, token info, tx decode, Chainlink price feed, payment verification) plus encoding, hashing, and data transformation utilities.
README
crypto-payments-mcp
An MCP server that lets AI agents read crypto wallets and prove on-chain payments across Ethereum and Solana.
It exists for one job: the x402 close-loop. Before an agent hands over work (an API response, a file, a result), it can verify the buyer's payment actually landed at the expected address — on-chain, with no backend and no API key.
Why this exists
Agents that sell things on-chain can't easily answer "did I get paid?" The primitives are not one-liners:
- Proving a transfer hit a specific recipient (native ETH/SOL or an ERC-20 like USDC)
- Reading an address's native + token balances
- Decoding what a transaction actually did
- Resolving ENS names so a payment request can arrive as
vitalik.eth
crypto-payments-mcp wraps those reads behind clean MCP tools so any agent client can call them.
Install
npx -y crypto-payments-mcp
Or add it to your agent's MCP config:
{
"mcpServers": {
"crypto-payments-mcp": {
"command": "npx",
"args": ["-y", "crypto-payments-mcp"]
}
}
}
Works with Claude, Cursor, Hermes, ElizaOS, and any MCP client.
A hosted HTTP endpoint is also available for remote clients:
https://crypto-payments-mcp.irun2themoney.workers.dev/mcp
Tools
| Tool | What it does |
|---|---|
verify_payment |
Confirm a payment reached the expected recipient (native ETH/SOL or ERC-20). The x402 close-loop. |
wallet_balance |
Native + ERC-20 balance for any address. |
token_info |
ERC-20 metadata (symbol, name, decimals) from a contract. |
decode_transaction |
From/to/value + ERC-20 transfer for an Ethereum tx. |
resolve_ens |
ENS name → address, or address → primary ENS name. |
chain_status |
Latest block/slot — a quick chain-liveness check. |
token_price |
Spot USD price via a Chainlink feed (no API key). |
transaction_history |
PREMIUM — recent transactions for an address (indexer view free RPCs can't give). Gated by an on-chain payment. |
How it works
- No API key, no backend, no accounts. On-chain reads use free public RPCs (llamarpc for ETH, Solana mainnet for SOL).
- Stateless and safe-fail. If a chain can't be reached, the tool reports the error instead of guessing.
- Zero dependencies. Pure Node stdlib — drop it into any agent runtime.
Premium tool (x402)
Six tools are free to drive adoption. transaction_history is premium: an agent pays our address on-chain, then calls again with the payment tx hash; the server verifies the payment via verify_payment before returning data. No backend, no accounts — the payment is the access key.
- Price:
0.5USDC (ERC-20),0.001ETH, or0.01SOL. - Receive: ETH/USDC
0xc62b0aCba58E2Fc31cE2d27721Ee51154a808f52, SOLD19x8rMGo9dCv98UGaNuv6SM2Xov8Q5TxCkjrmfeynmn
License
MIT. Free to use, modify, and ship inside your own agent.
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.
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.
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.