Direct Solana blockchain interaction via JSON-RPC — account lookups, token balances, transaction submission, and program queries
npx skills add https://github.com/agiprolabs/claude-trading-skills --skill solana-rpc
The Solana JSON-RPC API provides direct read/write access to the blockchain. Use it for account state queries, token balance lookups, transaction building and submission, and program account enumeration. This is the low-level foundation when higher-level APIs (Birdeye, Helius, SolanaTracker) don't have the data you need.
import httpx
RPC = os.getenv("SOLANA_RPC_URL", "https://api.mainnet-beta.solana.com")
def rpc_call(method: str, params: list = None) -> dict:
resp = httpx.post(RPC, json={
"jsonrpc": "2.0", "id": 1,
"method": method, "params": params or [],
}, timeout=30.0)
return resp.json()
# Get SOL balance
result = rpc_call("getBalance", ["WALLET_PUBKEY"])
sol_balance = result["result"]["value"] / 1e9
# Get latest blockhash
result = rpc_call("getLatestBlockhash")
blockhash = result["result"]["value"]["blockhash"]
| Provider | Free Tier | Paid | Notes |
|----------|-----------|------|-------|
| Helius | 50K credits/day | $49+/mo | Enhanced RPCs, DAS API |
| QuickNode | Limited | $49+/mo | Multi-chain, WebSocket |
| Triton | No free tier | ~$300+/mo | Yellowstone gRPC bundled |
| Shyft | Limited | $49+/mo | Yellowstone gRPC bundled |
| Alchemy | 300M CU/mo | Scaling | Good free tier |
| Public (mainnet-beta) | Free | — | Rate limited, unreliable |
Recommendation: Use Helius or QuickNode for development. Never use public RPC for production trading.
# SOL balance (in lamports, divide by 1e9 for SOL)
getBalance(pubkey, {commitment: "confirmed"})
# Full account info (data, owner, lamports, executable)
getAccountInfo(pubkey, {encoding: "jsonParsed"})
# Multiple accounts in one call
getMultipleAccounts([pubkey1, pubkey2], {encoding: "jsonParsed"})
# All SPL token accounts owned by a wallet
getTokenAccountsByOwner(wallet_pubkey, {
"programId": "TokenkegQfeZyiNwAJbNbGKPFXCWuBvf9Ss623VQ5DA"
}, {"encoding": "jsonParsed"})
# Token balance for a specific token account
getTokenAccountBalance(token_account_pubkey)
# Largest token accounts (top holders)
getTokenLargestAccounts(mint_pubkey)
# Total supply of a token
getTokenSupply(mint_pubkey)
# Get parsed transaction by signature
getTransaction(signature, {
"encoding": "jsonParsed",
"maxSupportedTransactionVersion": 0,
})
# Recent transaction signatures for an address
getSignaturesForAddress(pubkey, {
"limit": 20,
"before": "optional_signature", # pagination cursor
})
# Transaction status
getSignatureStatuses([sig1, sig2])
# Current slot
getSlot({commitment: "confirmed"})
# Block data
getBlock(slot, {
"encoding": "jsonParsed",
"transactionDetails": "full",
"maxSupportedTransactionVersion": 0,
})
# Latest blockhash (needed for tx building)
getLatestBlockhash({commitment: "confirmed"})
# Slot leader schedule
getLeaderSchedule()
# All accounts owned by a program (with filters)
getProgramAccounts(program_pubkey, {
"encoding": "jsonParsed",
"filters": [
{"dataSize": 165}, # Filter by account data size
{"memcmp": { # Filter by data content
"offset": 32,
"bytes": "base58_encoded_value",
}},
],
})
Warning: getProgramAccounts without filters can return millions of results and timeout. Always use dataSize and/or memcmp filters.
# Recent priority fee estimates
getRecentPrioritizationFees([account_pubkey])
# Returns array of { slot, prioritizationFee } for recent slots
# Minimum rent for account
getMinimumBalanceForRentExemption(data_length)
# Send a signed, serialized transaction
sendTransaction(base64_tx, {
"encoding": "base64",
"skipPreflight": False,
"preflightCommitment": "confirmed",
"maxRetries": 3,
})
# Simulate before sending
simulateTransaction(base64_tx, {
"encoding": "base64",
"sigVerify": False,
"commitment": "confirmed",
})
import time
def confirm_transaction(rpc_url: str, signature: str, timeout: float = 30.0) -> bool:
"""Poll for transaction confirmation."""
start = time.time()
while time.time() - start < timeout:
result = rpc_call("getSignatureStatuses", [[signature]])
statuses = result.get("result", {}).get("value", [None])
if statuses[0] is not None:
status = statuses[0]
if status.get("err"):
return False
if status.get("confirmationStatus") in ("confirmed", "finalized"):
return True
time.sleep(0.5)
return False
| Level | Description | Use When |
|-------|-------------|----------|
| processed | Single node confirmation | Speed over safety |
| confirmed | Supermajority (2/3+) | Default for trading |
| finalized | Maximum supermajority + 31 slots | Critical operations |
Always specify commitment explicitly. Default varies by provider.
def get_wallet_tokens(wallet: str) -> list[dict]:
"""Get all SPL token holdings with metadata."""
result = rpc_call("getTokenAccountsByOwner", [
wallet,
{"programId": "TokenkegQfeZyiNwAJbNbGKPFXCWuBvf9Ss623VQ5DA"},
{"encoding": "jsonParsed"},
])
tokens = []
for acct in result["result"]["value"]:
info = acct["account"]["data"]["parsed"]["info"]
tokens.append({
"mint": info["mint"],
"amount": int(info["tokenAmount"]["amount"]),
"decimals": info["tokenAmount"]["decimals"],
"ui_amount": info["tokenAmount"]["uiAmount"],
})
return [t for t in tokens if t["amount"] > 0]
def get_top_holders(mint: str) -> list[dict]:
"""Get the 20 largest holders of a token."""
result = rpc_call("getTokenLargestAccounts", [mint])
supply_result = rpc_call("getTokenSupply", [mint])
total_supply = int(supply_result["result"]["value"]["amount"])
holders = []
for acct in result["result"]["value"]:
amount = int(acct["amount"])
holders.append({
"address": acct["address"],
"amount": amount,
"decimals": acct["decimals"],
"ui_amount": acct["uiAmount"],
"percentage": amount / total_supply * 100 if total_supply > 0 else 0,
})
return holders
def rpc_batch(calls: list[tuple[str, list]]) -> list[dict]:
"""Execute multiple RPC calls in a single HTTP request."""
payload = [
{"jsonrpc": "2.0", "id": i, "method": method, "params": params}
for i, (method, params) in enumerate(calls)
]
resp = httpx.post(RPC, json=payload, timeout=30.0)
results = resp.json()
results.sort(key=lambda r: r["id"])
return [r.get("result") for r in results]
| Program | ID |
|---------|-----|
| System | 11111111111111111111111111111111 |
| SPL Token | TokenkegQfeZyiNwAJbNbGKPFXCWuBvf9Ss623VQ5DA |
| Token-2022 | TokenzQdBNbLqP5VEhdkAS6EPFLC1PHnBqCXEpPxuEb |
| Associated Token | ATokenGPvbdGVxr1b2hvZbsiqW5xWH25efTNsLJA8knL |
| Raydium AMM | 675kPX9MHTjS2zt1qfr1NYHuzeLXfQM9H24wFSUt1Mp8 |
| Raydium CLMM | CAMMCzo5YL8w4VFF8KVHrK22GGUsp5VTaW7grrKgrWqK |
| Orca Whirlpool | whirLbMiicVdio4qvUfM5KAg6Ct8VwpYzGff3uctyCc |
| Meteora DLMM | LBUZKhRxPF3XUpBCjp4YzTKgLccjZhTSDM9YuVaPwxo |
| PumpFun | 6EF8rrecthR5Dkzon8Nwu78hRvfCKubJ14M5uBEwF6P |
| Jupiter v6 | JUP6LkbZbjS1jKKwapdHNy74zcZ3tLUZoi5QNyVTaV4 |
| Compute Budget | ComputeBudget111111111111111111111111111111 |
| Need | Use |
|------|-----|
| Token balance check | Direct RPC (getTokenAccountsByOwner) |
| Top 20 holders | Direct RPC (getTokenLargestAccounts) |
| Historical OHLCV | Birdeye or SolanaTracker |
| Parsed transaction history | Helius Enhanced Transactions |
| Token metadata (name, image) | Helius DAS API |
| Real-time streaming | Yellowstone gRPC |
| Wallet PnL tracking | SolanaTracker |
| Token risk scoring | SolanaTracker |
| Cross-chain data | DexScreener or CoinGecko |
references/methods.md — Complete RPC method reference with parameters and response schemasreferences/error_handling.md — Error codes, rate limits, timeout handling, retry strategiesreferences/providers.md — RPC provider comparison with pricing and featuresscripts/wallet_scanner.py — Scan wallet for all token holdings with balancesscripts/token_holders.py — Get top holders and concentration metrics for any tokenAutomatically organizes invoices and receipts for tax preparation by reading messy files, extracting key information, renaming them consistently, and sorting them into logical folders. Turns hours of manual bookkeeping into minutes of automated organization.
Expert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating quantitative trading strategies. Covers "beating ideas to death" methodology, parameter robustness testing, slippage modeling, bias prevention, and interpreting backtest results. Applicable when user asks about backtesting, strategy validation, robustness testing, avoiding overfitting, or systematic trading development.
This skill calculates key financial ratios and metrics from financial statement data for investment analysis
This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions
This skill retrieves upcoming earnings announcements for US stocks using the Financial Modeling Prep (FMP) API. Use this when the user requests earnings calendar data, wants to know which companies are reporting earnings in the upcoming week, or needs a weekly earnings review. The skill focuses on mid-cap and above companies (over $2B market cap) that have significant market impact, organizing the data by date and timing in a clean markdown table format. Supports multiple environments (CLI, Desktop, Web) with flexible API key management.
Crypto wallet operations via the awal CLI — sign in, check balances, send USDC/ETH/POL/SOL, trade tokens, fund the wallet, and use the x402 payment protocol to discover paid services, pay for API calls, monetize an API, or query onchain data. Use whenever the user mentions signing in, login, authentication, wallet status, balance, address, sending money, paying someone, transferring tokens, ENS names, swapping/trading/converting tokens, funding/topping up/onramp, USDC, ETH, POL, SOL, the x402 bazaar, paid APIs, monetizing an endpoint, or querying onchain data on Base.
Access real-time and historical stock market data, forex rates, cryptocurrency prices, commodities, economic indicators, and 50+ technical indicators via the Alpha Vantage API. Use when fetching stock prices (OHLCV), company fundamentals (income statement, balance sheet, cash flow), earnings, options data, market news/sentiment, insider transactions, GDP, CPI, treasury yields, gold/silver/oil prices, Bitcoin/crypto prices, forex exchange rates, or calculating technical indicators (SMA, EMA, MACD, RSI, Bollinger Bands). Requires a free API key from alphavantage.co.
Braintree Automation: manage payment processing via Stripe-compatible tools for customers, subscriptions, payment methods, and transactions
Take agiprolabs/solana-rpc from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.