Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when the user needs raw blockchain JSON-RPC access — contract reads (eth_call), native balances, blocks, transactions, logs, gas estimates, or any chain-native RPC method across 40 chains. One endpoint per chain via BlockRun's Tatum-backed gateway, $0.0040 per call, no node, no API key. Prefer blockrun_price / blockrun_dex / blockrun_surf when they already cover the question.
.claude/skills/blockrunai-rpc/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -24% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-12 | ✓→✗ | ▼ Worse | 49% | 0% |
blockrun_rpc POSTs a standard JSON-RPC 2.0 body to /v1/rpc/{network}. Flat $0.0030 per call ($0.002 base + the $0.001 transaction fee). A JSON-RPC batch array charges per element but pays the flat fee only once — $0.002 × n + $0.001, so a batch of 3 costs $0.0070 where three separate calls cost $0.0090. Batch whenever you can. Settlement in USDC via x402. Responses are cached briefly server-side for identical read calls (X-Cache: HIT is free of upstream latency but still billed).
| Question | Tool | |---|---| | "What's ETH trading at?" | blockrun_price (free) | | "PEPE/WETH pool liquidity?" | blockrun_dex (free) | | "What's this wallet labeled as / holding?" | blockrun_surf | | "Call balanceOf(0x...) on this ERC-20" | blockrun_rpc | | "Latest block / tx receipt / event logs / gas price" | blockrun_rpc | | "Solana account info / slot / signatures" | blockrun_rpc |
EVM (use eth_* methods):
| Key | Chain | | Key | Chain | |---|---|---|---|---| | ethereum | Ethereum | | zksync | zkSync Era | | base | Base | | berachain | Berachain | | arbitrum | Arbitrum One | | unichain | Unichain | | arbitrum-nova | Arbitrum Nova | | monad | Monad | | optimism | Optimism | | chiliz | Chiliz | | polygon | Polygon | | moonbeam | Moonbeam | | bsc | BNB Smart Chain | | aurora | Aurora | | avalanche | Avalanche C-Chain | | flare | Flare | | fantom | Fantom | | oasis | Oasis Sapphire | | cronos | Cronos | | kaia | Kaia (Klaytn) | | celo | Celo | | sonic | Sonic | | gnosis | Gnosis | | xdc | XDC Network | | abstract | Abstract | | hyperevm | HyperEVM | | plume | Plume | | ronin | Ronin | | rootstock | Rootstock (RSK) | | | |
Non-EVM (chain-native methods):
| Key | Chain | Method family | |---|---|---| | solana | Solana | getSlot, getBalance, getAccountInfo, getSignaturesForAddress | | bitcoin | Bitcoin | getblockchaininfo, getblockcount, getrawtransaction | | litecoin / dogecoin / bitcoin-cash / zcash | UTXO chains | Bitcoin-style RPC | | near | NEAR | status, query | | sui | Sui | sui_getLatestCheckpointSequenceNumber, suix_getBalance | | ripple | XRP Ledger | account_info, ledger | | polkadot / kusama | Substrate | chain_getHeader, state_getStorage |
Unknown-but-wellformed slugs pass through to the Tatum gateway untouched — newly added chains work without an MCP update. A bad slug returns HTTP 400 with the supported list (no charge).
ERC-20 balance (eth_call):
blockrun_rpc({
network: "base",
method: "eth_call",
params: [{
to: "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913", // USDC on Base
data: "0x70a08231000000000000000000000000<ADDRESS_NO_0x_PADDED_TO_32B>"
}, "latest"]
})Native balance: method: "eth_getBalance", params: ["0x...", "latest"] Tx receipt: method: "eth_getTransactionReceipt", params: ["0x<txhash>"] Event logs: method: "eth_getLogs", params: [{ fromBlock, toBlock, address, topics }] — keep ranges small; huge ranges are rejected upstream (no charge). Gas: method: "eth_gasPrice" / eth_estimateGas
Solana token account: network: "solana", method: "getTokenAccountsByOwner", params: ["<owner>", {"mint": "<mint>"}, {"encoding": "jsonParsed"}]
Batch (charged per element, flat fee paid once — 3 calls = $0.0070, vs $0.0090 sent separately):
blockrun_rpc({ network: "ethereum", body: [
{ jsonrpc: "2.0", id: 1, method: "eth_blockNumber" },
{ jsonrpc: "2.0", id: 2, method: "eth_gasPrice" },
{ jsonrpc: "2.0", id: 3, method: "eth_chainId" }
]})eth_call) come back inside result.error — the call is charged (the node did the work).| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-07 | pass→pass | 9,442 | 6,886 | -27% | 1 | 1 | 0% | 2,222 | 2,926 | +32% | 0 | 0 | — |
case-12 | pass→fail | 6,297 | 4,674 | -26% | 1 | 1 | 0% | 1,034 | 1,543 | +49% | 0 | 0 | — |
case-01 | fail→fail | 7,944 | 7,272 | -8% | 1 | 1 | 0% | 1,598 | 1,903 | +19% | 0 | 0 | — |
case-02 | pass→fail | 9,088 | 6,873 | -24% | 1 | 1 | 0% | 1,839 | 1,875 | +2% | 0 | 0 | — |
case-03 | fail→fail | 8,946 | 7,471 | -16% | 1 | 1 | 0% | 1,762 | 1,857 | +5% | 0 | 0 | — |
case-04 | fail→fail | 3,463 | 11,226 | +224% | 1 | 1 | 0% | 493 | 2,429 | +393% | 0 | 0 | — |
case-05 | pass→fail | 4,439 | 5,356 | +21% | 1 | 1 | 0% | 661 | 1,673 | +153% | 0 | 0 | — |
case-06 | pass→fail | 7,561 | 5,762 | -24% | 1 | 1 | 0% | 1,327 | 1,811 | +36% | 0 | 0 | — |
case-08 | pass→pass | 9,723 | 5,207 | -46% | 1 | 1 | 0% | 1,934 | 2,302 | +19% | 0 | 0 | — |
case-09 | pass→fail | 7,605 | 6,539 | -14% | 1 | 1 | 0% | 1,473 | 1,742 | +18% | 0 | 0 | — |
case-10 | pass→fail | 8,001 | 8,400 | +5% | 1 | 1 | 0% | 1,590 | 1,848 | +16% | 0 | 0 | — |
case-11 | fail→pass | 10,934 | 4,671 | -57% | 1 | 1 | 0% | 2,117 | 2,199 | +4% | 0 | 0 | — |
case-13 | fail→fail | 13,765 | 11,856 | -14% | 1 | 1 | 0% | 1,486 | 2,312 | +56% | 0 | 0 | — |
case-14 | fail→pass | 11,803 | 3,524 | -70% | 1 | 1 | 0% | 2,232 | 2,157 | -3% | 0 | 0 | — |
case-15 | pass→pass | 10,780 | 5,708 | -47% | 1 | 1 | 0% | 1,843 | 2,327 | +26% | 0 | 0 | — |
case-16 | fail→pass | 15,276 | 4,384 | -71% | 1 | 1 | 0% | 2,727 | 2,076 | -24% | 0 | 0 | — |
case-17 | pass→pass | 7,340 | 1,971 | -73% | 1 | 1 | 0% | 1,150 | 1,692 | +47% | 0 | 0 | — |
case-18 | fail→pass | 14,333 | 2,628 | -82% | 1 | 1 | 0% | 2,198 | 1,723 | -22% | 0 | 0 | — |
case-19 | fail→fail | 10,314 | 5,416 | -47% | 1 | 1 | 0% | 1,952 | 1,584 | -19% | 0 | 0 | — |
case-20 | fail→fail | 6,924 | 5,415 | -22% | 1 | 1 | 0% | 1,241 | 1,675 | +35% | 0 | 0 | — |
case-21 | pass→fail | 10,663 | 6,250 | -41% | 1 | 1 | 0% | 2,085 | 1,677 | -20% | 0 | 0 | — |
case-22 | pass→fail | 8,425 | 4,694 | -44% | 1 | 1 | 0% | 1,662 | 1,594 | -4% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 8 counted toward the lift figure. The other 14 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of -18 percentage points is the difference between those two pass rates over the 8 comparable cases. 9 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.