Blockchain JSON-RPC on 23 EVM chains for AI agents - free tier, API key, or x402 pay-per-call.
Connect Nodeflare to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Blockchain JSON-RPC on 23 EVM chains for AI agents - free tier, API key, or x402 pay-per-call. The nodeflare mcp server is what makes that connection.
Blockchain JSON-RPC for AI agents on 23 EVM chains — Ethereum, Base, BNB Chain, Arbitrum, Optimism, Avalanche, HyperEVM, Polygon, and young chains like Robinhood Chain, Plasma, Ink, Zircuit, BOB and Soneium. Served from NodeFlare's own bare-metal nodes across 5 regions.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
list_chains — The 23 supported chains with chain IDs and endpointsget_block_number — Latest block number (decimal + hex)get_balance — Native-token balance — raw wei + human-readable amount in the chain's currencyget_transaction_receipt — Transaction receipt by hasheth_call — Read-only contract callget_logs — Contract event logs (heavy — key or x402 wallet)rpc_call — Any JSON-RPC method on any supported chainget_transaction — Transaction by hash (from, to, value, input)get_block — Block by number/tag, optional full transactionsget_gas_price — Current gas price + EIP-1559 priority feeget_token_balance — ERC-20 balance, raw + human-readableget_token_metadata — ERC-20 name, symbol, decimals, total supplyConfiguration is passed through the environment: X402_PRIVATE_KEY, NODEFLARE_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.
Plenty of monitoring and observability servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Nodeflare's toolset — list_chains, get_block_number, get_balance and 11 more — is a fair guide to whether it matches your workflow. It is maintained by Nodeflare-app; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| list_chains | The 23 supported chains with chain IDs and endpoints |
| get_block_number | Latest block number (decimal + hex) |
| get_balance | Native-token balance — raw wei + human-readable amount in the chain's currency |
| get_transaction_receipt | Transaction receipt by hash |
| eth_call | Read-only contract call |
| get_logs | Contract event logs (heavy — key or x402 wallet) |
| rpc_call | Any JSON-RPC method on any supported chain |
| get_transaction | Transaction by hash (from, to, value, input) |
| get_block | Block by number/tag, optional full transactions |
| get_gas_price | Current gas price + EIP-1559 priority fee |
| get_token_balance | ERC-20 balance, raw + human-readable |
| get_token_metadata | ERC-20 name, symbol, decimals, total supply |
| resolve_ens | ENS name → address (forward) or address → primary ENS name (reverse) |
| get_token_price | Current USD price of an ERC-20 (DefiLlama, keyless) — price, symbol, confidence |
{
"mcpServers": {
"nodeflare": {
"command": "npx",
"args": ["-y", "nodeflare-mcp"]
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| X402_PRIVATE_KEY | Credential the server authenticates with. | Yes |
| NODEFLARE_API_KEY | Credential the server authenticates with. | Yes |
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Dashboards, Prometheus and Loki queries, incidents and alerts — observability by conversation.
Errors with full context — stack traces, issue triage and AI-powered root-cause analysis from Sentry's server.
Enables enhanced web research capabilities for large language models through intelligent search queuing and advanced content extraction.
Automates browser interactions and enables Large Language Models (LLMs) to interact with web pages through Playwright and Chrome DevTools Protocol
Guides tool usage by providing recommendations for MCP tools at each problem-solving stage.