aeX402 — Cross-Chain DeFi MCP: LINQ, AMM, Bridge, AI
Agent MCP for DeFi: cross-chain LINQ fan-out, AMM quotes/swaps, bridge, AI. Solana+EVM. Free+x402.
Should I use this
Quality & Safety
Findings (15)
- HIGHTool poisoning patterns detected
- MEDIUMTool description contains suspicious base64-like encoded stringin aex402_listPools
- MEDIUMTool description contains suspicious base64-like encoded stringin solana_rpc
- LOWTool 'solana_getBalance' doesn't follow camelCase/snake_casein solana_getBalance
- LOWTool 'solana_getAccountInfo' doesn't follow camelCase/snake_casein solana_getAccountInfo
- LOWTool 'solana_getTokenAccountsByOwner' doesn't follow camelCase/snake_casein solana_getTokenAccountsByOwner
- LOWTool 'solana_getTransaction' doesn't follow camelCase/snake_casein solana_getTransaction
- LOWTool 'solana_getLatestBlockhash' doesn't follow camelCase/snake_casein solana_getLatestBlockhash
- LOWTool 'solana_getSignaturesForAddress' doesn't follow camelCase/snake_casein solana_getSignaturesForAddress
- LOWTool 'solana_sendTransaction' doesn't follow camelCase/snake_casein solana_sendTransaction
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"rpc": {
"url": "https://rpc.aex402.com/mcp"
}
}
}Remote endpoints
https://rpc.aex402.com/mcpstreamable-httpWhat it can do
Tool inventory
Tools (33)
🟢solana_getBalance(address)
Get SOL balance for a wallet address (in lamports). Divide by 1e9 for SOL.
Input Schema
{
"type": "object",
"properties": {
"address": {
"type": "string",
"description": "Solana wallet address (base58)"
}
},
"required": [
"address"
]
}Output Schema
{
"type": "object",
"properties": {
"context": {
"type": "object",
"properties": {
"slot": {
"type": "integer",
"description": "slot the value was read at"
}
}
},
"value": {
"type": "integer",
"description": "balance in lamports (1e9 = 1 SOL)"
}
},
"required": [
"context",
"value"
]
}🟢solana_getAccountInfo(address, encoding)
Get raw account info (owner, lamports, data) for any Solana address.
Input Schema
{
"type": "object",
"properties": {
"address": {
"type": "string",
"description": "Account address (base58)"
},
"encoding": {
"type": "string",
"description": "Data encoding: base64 (default) or jsonParsed",
"default": "base64"
}
},
"required": [
"address"
]
}Output Schema
{
"type": "object",
"properties": {
"context": {
"type": "object",
"properties": {
"slot": {
"type": "integer",
"description": "slot the value was read at"
}
}
},
"value": {
"type": [
"object",
"null"
],
"description": "account (lamports, owner, data, executable, rentEpoch) or null if it does not exist"
}
},
"required": [
"context"
]
}🟢solana_getTokenAccountsByOwner(owner)
Get all SPL token accounts owned by a wallet. Returns mint, balance, decimals for each token.
Input Schema
{
"type": "object",
"properties": {
"owner": {
"type": "string",
"description": "Wallet address (base58)"
}
},
"required": [
"owner"
]
}Output Schema
{
"type": "object",
"properties": {
"context": {
"type": "object",
"properties": {
"slot": {
"type": "integer",
"description": "slot the value was read at"
}
}
},
"value": {
"type": "array",
"items": {
"type": "object",
"properties": {
"pubkey": {
"type": "string",
"description": "token account address"
},
"account": {
"type": "object",
"description": "parsed SPL account (mint, owner, tokenAmount)"
}
}
}
}
},
"required": [
"context",
"value"
]
}🟢solana_getTransaction(signature)
Get full transaction details by signature, including instructions, logs, and status.
Input Schema
{
"type": "object",
"properties": {
"signature": {
"type": "string",
"description": "Transaction signature (base58)"
}
},
"required": [
"signature"
]
}Output Schema
{
"type": "object",
"properties": {
"slot": {
"type": "integer"
},
"blockTime": {
"type": [
"integer",
"null"
],
"description": "unix seconds"
},
"transaction": {
"type": "object",
"description": "message + signatures"
},
"meta": {
"type": "object",
"description": "fee, pre/post balances, logs, err"
}
}
}🟢solana_getLatestBlockhash
Get latest blockhash for transaction building. Returns blockhash + lastValidBlockHeight.
Input Schema
{
"type": "object",
"properties": {}
}Output Schema
{
"type": "object",
"properties": {
"context": {
"type": "object",
"properties": {
"slot": {
"type": "integer",
"description": "slot the value was read at"
}
}
},
"value": {
"type": "object",
"properties": {
"blockhash": {
"type": "string",
"description": "base58"
},
"lastValidBlockHeight": {
"type": "integer"
}
},
"required": [
"blockhash",
"lastValidBlockHeight"
]
}
},
"required": [
"context",
"value"
]
}🟢solana_getSignaturesForAddress(address, limit)
Get recent transaction signatures for an address. Returns up to 20 most recent.
Input Schema
{
"type": "object",
"properties": {
"address": {
"type": "string",
"description": "Account address (base58)"
},
"limit": {
"type": "number",
"description": "Max signatures to return (default 20, max 1000)",
"default": 20
}
},
"required": [
"address"
]
}Output Schema
{
"type": "object",
"properties": {
"result": {
"type": "array",
"items": {
"type": "object",
"properties": {
"signature": {
"type": "string",
"description": "base58 tx signature"
},
"slot": {
"type": "integer"
},
"err": {
"type": [
"object",
"null"
]
},
"blockTime": {
"type": [
"integer",
"null"
]
},
"confirmationStatus": {
"type": "string"
}
}
}
}
},
"required": [
"result"
],
"description": "array of recent signature records, newest first"
}🟡solana_sendTransaction(transaction)
Submit a signed transaction to the network. Returns transaction signature.
Input Schema
{
"type": "object",
"properties": {
"transaction": {
"type": "string",
"description": "Base64-encoded signed transaction"
}
},
"required": [
"transaction"
]
}Output Schema
{
"type": "object",
"properties": {
"result": {
"type": "string",
"description": "base58 transaction signature"
}
},
"required": [
"result"
],
"description": "signature of the submitted transaction"
}🟢solana_getSlot
Get the current slot number.
Input Schema
{
"type": "object",
"properties": {}
}Output Schema
{
"type": "object",
"properties": {
"result": {
"type": "integer",
"description": "current slot"
}
},
"required": [
"result"
],
"description": "current slot number"
}🟢aex402_listPools(minTvl)
List all AeX402 AMM pools on Solana. Returns pool addresses with basic info (mints, balances, fee, amp). Pools are 1024-byte accounts owned by program 3AMM53MsJZy2Jvf7PeHHga3bsGjWV4TSaYz29WUtcdje.
Input Schema
{
"type": "object",
"properties": {
"minTvl": {
"type": "number",
"description": "Minimum TVL in lamports to filter (default 0)",
"default": 0
}
}
}Output Schema
{
"type": "object",
"properties": {
"count": {
"type": "integer"
},
"pools": {
"type": "array",
"items": {
"type": "object",
"description": "pool summary: address, mints, balances, tvl, feeBps, amp"
}
}
},
"required": [
"count",
"pools"
]
}🟢aex402_getPool(address)
Get detailed AeX402 pool info: token mints, balances, fee, amplification, LP supply, analytics (OHLCV candles), circuit breaker status.
Input Schema
{
"type": "object",
"properties": {
"address": {
"type": "string",
"description": "Pool account address (base58)"
}
},
"required": [
"address"
]
}Output Schema
{
"type": "object",
"properties": {
"address": {
"type": "string"
},
"authority": {
"type": "string"
},
"token0Mint": {
"type": "string"
},
"token1Mint": {
"type": "string"
},
"vault0": {
"type": "string"
},
"vault1": {
"type": "string"
},
"lpMint": {
"type": "string"
},
"amp": {
"type": "string",
"description": "u64 as string"
},
"feeBps": {
"type": "string",
"description": "basis points as string"
},
"balance0": {
"type": "string",
"description": "u64 as string"
},
"balance1": {
"type": "string",
"description": "u64 as string"
},
"lpSupply": {
"type": "string",
"description": "u64 as string"
},
"paused": {
"type": "boolean"
},
"analytics": {
"type": "object",
"description": "OHLCV candles + trade stats"
}
},
"required": [
"address"
],
"description": "full pool state"
}🟢aex402_quote(pool, inputMint, amount)
Get a swap quote from an AeX402 pool. Calculates expected output, price impact, and fees without executing.
Input Schema
{
"type": "object",
"properties": {
"pool": {
"type": "string",
"description": "Pool account address (base58)"
},
"inputMint": {
"type": "string",
"description": "Input token mint address"
},
"amount": {
"type": "number",
"description": "Input amount in atomic units (lamports/smallest unit)"
}
},
"required": [
"pool",
"inputMint",
"amount"
]
}Output Schema
{
"type": "object",
"properties": {
"inputMint": {
"type": "string"
},
"inputAmount": {
"type": "string",
"description": "u64 as string"
},
"outputMint": {
"type": "string"
},
"estimatedOutput": {
"type": "string",
"description": "u64 as string"
},
"feeBps": {
"type": "integer"
},
"priceImpactPct": {
"type": "string",
"description": "percent, 4 decimals"
},
"note": {
"type": "string"
}
},
"required": [
"inputMint",
"inputAmount",
"outputMint",
"estimatedOutput"
]
}🟡aex402_rh_pool
Get the live state of the aeX402 AMM on Robinhood Chain (EVM 4663) — the diamond-contract port of the Solana AMM. The AMM is the set of GRADUATED launchpad coins whose pools are seeded in-diamond on the canonical launchpad (0xED2F); this enumerates them live by scanning VPoolGraduated events + reading each pool's reserves, so it tracks reality as coins graduate. Returns graduatedPools[] (poolId, token, reserves, TVL), graduatedPoolCount, and status ("live" | "no-graduated-pools" | "unknown"), plus the legacy standalone 0xA1F6 USDG/WETH pool (legacy-drained). Distinct from the chain's Uniswap-fork DEX. No inputs.
Input Schema
{
"type": "object",
"properties": {}
}🟡launch_token(name, ticker, creator, description, image, ...)
Launch a memecoin on the aeX402 launchpad on Robinhood Chain (EVM 4663) for a FIXED pump.fun-style bonding curve (1B supply, starts 0.0001 USDG, graduates at 10,000 USDG raised, quoted in USDG). You supply only identity — name + ticker (+ optional description/image/links). DEFAULT (custodial): the aeX402 backend SIGNS + SUBMITS the createVPool tx for you, so a claude.ai user with NO WALLET can launch in one call; returns {ok,status,txHash,vpId}. Optionally pass `creator` (a 0x address) to record as the coin owner. Pass build:true instead to get an UNSIGNED tx {to,value,data} to submit yourself (non-custodial — that requires `creator` and makes you the on-chain creator). A custodial call SIMULATES first, so a failure burns no gas: status "gated" means createVPool reverts in simulation (cause not determined — likeliest are the ticker still being claimed by a bonding coin or this vpId being taken; see `detail`/`revertData`), and status "unreachable" means the chain could not be reached, which is retryable. The launchpad is NOT chain-gated: createVPool simulates clean from an arbitrary sender (measured 2026-09-25).
Input Schema
{
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Token name, 1..32 bytes (e.g. \"Fork Meme\")"
},
"ticker": {
"type": "string",
"description": "Ticker / symbol, 1..16 bytes (e.g. \"FMEME\")"
},
"creator": {
"type": "string",
"description": "OPTIONAL 0x EVM address recorded as the coin owner (and seeds the vpId). REQUIRED only when build:true (then it is the self-signing on-chain creator)."
},
"description": {
"type": "string",
"description": "Short description (<=256 chars) — off-chain metadata"
},
"image": {
"type": "string",
"description": "Image URL (https:// or ipfs:// only) — off-chain metadata"
},
"links": {
"type": "array",
"items": {
"type": "string"
},
"description": "Up to 3 links (https:// or ipfs:// only) — off-chain metadata"
},
"pad": {
"type": "string",
"description": "OPTIONAL aeX402 launchpad slug the coin is launched on. Its vpId then starts with that pad's tag, so the pad lists it. Applies on BOTH the custodial (default) and build:true paths"
},
"build": {
"type": "boolean",
"description": "If true, return an UNSIGNED tx to submit yourself (non-custodial) instead of the backend launching for you. Default false."
}
},
"required": [
"name",
"ticker"
]
}Output Schema
{
"type": "object",
"properties": {
"ok": {
"type": "boolean",
"description": "Custodial mode: whether the launch was submitted"
},
"status": {
"type": "string",
"description": "submitted | gated | custodial-disabled | exists | rate-limited | insufficient-gas | submit-failed"
},
"txHash": {
"type": "string",
"description": "Custodial mode: the createVPool tx hash"
},
"vpId": {
"type": "string",
"description": "Deterministic keccak256(creator-or-launcher ++ name ++ ticker)"
},
"to": {
"type": "string",
"description": "build mode: aeX402 diamond address"
},
"data": {
"type": "string",
"description": "build mode: createVPool calldata to submit"
},
"metadata": {
"type": "object",
"description": "Off-chain metadata (stored server-side in custodial mode)"
},
"note": {
"type": "string"
}
}
}⚪solana_buildTransfer(from, to, amount, mint)
Build a SOL or SPL token transfer instruction. Returns instruction JSON (programId, keys, data) for client-side TX construction and signing.
Input Schema
{
"type": "object",
"properties": {
"from": {
"type": "string",
"description": "Sender wallet address (base58)"
},
"to": {
"type": "string",
"description": "Recipient address (base58)"
},
"amount": {
"type": "number",
"description": "Amount in atomic units (lamports for SOL, smallest unit for SPL)"
},
"mint": {
"type": "string",
"description": "SPL token mint address. Omit for native SOL transfer."
}
},
"required": [
"from",
"to",
"amount"
]
}Output Schema
{
"type": "object",
"properties": {
"action": {
"type": "string",
"description": "'transfer_sol' or 'transfer_spl'"
},
"instruction": {
"type": "object",
"properties": {
"programId": {
"type": "string"
},
"keys": {
"type": "array",
"items": {
"type": "object",
"description": "pubkey/isSigner/isWritable"
}
},
"data": {
"type": "string",
"description": "base64 instruction data"
}
},
"required": [
"programId",
"keys",
"data"
]
},
"summary": {
"type": "string",
"description": "human-readable description of the transfer being built"
}
},
"required": [
"action",
"instruction"
]
}⚪aex402_buildSwap(pool, inputMint, amount, slippageBps, userWallet)
Build an AeX402 AMM swap action. Fetches live pool state, computes output with slippage protection, returns all instruction parameters and account addresses for client signing.
Input Schema
{
"type": "object",
"properties": {
"pool": {
"type": "string",
"description": "Pool account address (base58)"
},
"inputMint": {
"type": "string",
"description": "Input token mint address"
},
"amount": {
"type": "number",
"description": "Input amount in atomic units"
},
"slippageBps": {
"type": "number",
"description": "Max slippage in basis points (default 50 = 0.5%)"
},
"userWallet": {
"type": "string",
"description": "User wallet address (for account derivation)"
}
},
"required": [
"pool",
"inputMint",
"amount",
"userWallet"
]
}Output Schema
{
"type": "object",
"properties": {
"action": {
"type": "string",
"description": "'aex402_swap'"
},
"quote": {
"type": "object",
"description": "estimatedOutput, minOutput, priceImpact"
},
"instruction": {
"type": "object",
"description": "programId, keys, data (base64) — sign & submit client-side"
}
},
"required": [
"action",
"instruction"
]
}⚪agent_delegate(session, role, message, model)
Delegate a task to an independent specialist AI agent session. The delegate runs with full tool access and returns its response. Useful for breaking complex tasks into subtasks. Max depth: 3.
Input Schema
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Existing session ID to resume, or omit to create new session"
},
"role": {
"type": "string",
"description": "Role for new agent (e.g. \"Solana pool analyst\", \"route optimizer\"). Ignored if resuming session."
},
"message": {
"type": "string",
"description": "Task or question for the delegate agent"
},
"model": {
"type": "string",
"description": "Model ID or alias (default: gpt-4o-mini)"
}
},
"required": [
"message"
]
}Output Schema
{
"type": "object",
"description": "delegate agent response (session, reply text, usage)"
}🟡ai_chat(model, messages, max_tokens, temperature, reasoning_effort)
Send a chat completion request to the aeX402 AI Router. Free tier: 3 calls/day. Paid: deducts credits based on token usage.
Input Schema
{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Model ID or alias: gpt-4o-mini (default), gpt-4o, claude-sonnet, claude-haiku, llama-70b, llama-8b, gemini-flash"
},
"messages": {
"type": "array",
"description": "Chat messages array [{role: \"user\"|\"system\"|\"assistant\", content: \"...\"}]",
"items": {
"type": "object",
"properties": {
"role": {
"type": "string",
"description": "Message role: system, user, or assistant"
},
"content": {
"type": "string",
"description": "Message content"
}
},
"required": [
"role",
"content"
]
}
},
"max_tokens": {
"type": "number",
"description": "Maximum tokens to generate (model-dependent default)"
},
"temperature": {
"type": "number",
"description": "Sampling temperature (0-2)"
},
"reasoning_effort": {
"type": "string",
"description": "low | medium | high — ask a reasoning-capable model to think harder. The chain-of-thought comes back in the tool result _meta (\"com.aex402/reasoning\")."
}
},
"required": [
"messages"
]
}Output Schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"object": {
"type": "string",
"description": "always 'chat.completion'"
},
"created": {
"type": "integer",
"description": "unix seconds"
},
"model": {
"type": "string"
},
"choices": {
"type": "array",
"items": {
"type": "object",
"properties": {
"message": {
"type": "object",
"description": "role + content"
},
"finish_reason": {
"type": "string"
}
}
}
},
"usage": {
"type": "object",
"description": "prompt/completion/total tokens"
}
},
"required": [
"choices"
],
"description": "OpenAI-compatible chat completion"
}🟢solana_rpc(method, params, network)
Call ANY Solana-compatible JSON-RPC method by name — full RPC surface beyond the typed solana_* tools (getProgramAccounts, getBlock, getEpochInfo, simulateTransaction, ...). Defaults to Solana mainnet; pass network:slonana to query Slonana (rpc.slonana.com), which additionally exposes RPC methods no other network has: getAlpenglowHealth (consensus migration status), getBridgeStatus, getAexchanRelays, getValidatorStats, quote. (listSvmNetworks/enableSvmNetwork/disableSvmNetwork/setNetworkRpcUrl also exist but are inert API-compat stubs — listSvmNetworks always reports one hardcoded network and the enable/disable/set calls ignore their arguments and return true; verified in source, not live network-management controls.) For tools that exist ONLY on Slonana's MCP server with no RPC-method equivalent (the aea_* agent registry), use mcp_call instead.
Input Schema
{
"type": "object",
"properties": {
"method": {
"type": "string",
"description": "Solana RPC method name, e.g. getEpochInfo"
},
"params": {
"type": "array",
"description": "Positional params array (method-specific). Omit for no params."
},
"network": {
"type": "string",
"description": "solana (default/mainnet-beta) or slonana",
"default": "solana"
}
},
"required": [
"method"
]
}🟢mcp_call(server, tool, arguments)
Call a tool on another MCP server this RPC federates with, for tools that have no equivalent in solana_rpc/evm_rpc (no underlying JSON-RPC method — e.g. Slonana's aea_list_services/aea_resolve agent registry). Known servers: slonana. Call that server's tools/list first if you don't know its tool names.
Input Schema
{
"type": "object",
"properties": {
"server": {
"type": "string",
"description": "Federated server name. One of: slonana"
},
"tool": {
"type": "string",
"description": "Tool name on that server, e.g. aea_list_services. Omit both tool and arguments to list that server's tools instead."
},
"arguments": {
"type": "object",
"description": "Arguments for the tool call, per that server's own schema."
}
},
"required": [
"server"
]
}⚪evm_rpc(method, params, network)
Call ANY EVM JSON-RPC method on a supported chain — eth_getBalance, eth_call, eth_blockNumber, eth_sendRawTransaction, eth_getLogs, ... Chains: robinhood (4663) / robinhood-testnet (46630), hyperevm (999), ethereum (1), base (8453), stable (988), plasma (9745), tempo (4217), codex (81224), arc (5042, Circle mainnet).
Input Schema
{
"type": "object",
"properties": {
"method": {
"type": "string",
"description": "EVM RPC method name, e.g. eth_getBalance"
},
"params": {
"type": "array",
"description": "Positional params array (method-specific). Omit for no params."
},
"network": {
"type": "string",
"description": "Chain slug: robinhood (default; legacy mainnet alias accepted), robinhood-testnet, hyperevm, ethereum/eth, base, stable/tether, plasma, tempo, codex, or arc (Circle mainnet)",
"default": "robinhood"
}
},
"required": [
"method"
]
}🟢mcp_linq(calls, reduce, pipeline, linq, concurrency, ...)
Primary LINQ-style MCP workflow tool. Run one bounded MCP call: fan out up to 32 READ-ONLY tool calls across chains, then compose the combined result with fluent chains like results.selectMany(...).where(...).groupBy(...).orderByDesc(...).take(...), JSON pipeline steps, or reducers. Use mcp_linq when you want one aggregate answer instead of N tool calls.
Input Schema
{
"type": "object",
"properties": {
"calls": {
"type": "array",
"minItems": 1,
"maxItems": 32,
"description": "Read-only MCP tool calls to run. Each call has {id?, tool, args?, pick?}. pick is a dot path into that call output; [] flattens arrays.",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Stable label for this subcall; defaults to tool:index."
},
"tool": {
"type": "string",
"description": "Read-only tool name, e.g. evm_rpc, solana_rpc, discover_programs, search_tokens, hl_info."
},
"args": {
"type": "object",
"additionalProperties": true,
"description": "Arguments for the subcall."
},
"pick": {
"type": "string",
"description": "Optional dot path to return from this subcall, e.g. count or programs[].activity."
}
},
"required": [
"tool"
]
}
},
"reduce": {
"type": "object",
"additionalProperties": {
"type": "object",
"properties": {
"op": {
"type": "string",
"enum": [
"count",
"sum",
"avg",
"min",
"max",
"top",
"groupCount",
"groupSum",
"groupAvg",
"concat",
"first"
]
},
"path": {
"type": "string",
"description": "Dot path into the batch result, e.g. results[].picked or results[].output.programs[].activity."
},
"by": {
"type": "string",
"description": "For group* reducers: dot path inside each selected item used as the group key."
},
"value": {
"type": "string",
"description": "For groupSum/groupAvg: numeric path inside each selected item. Defaults to the item itself."
},
"sortBy": {
"type": "string",
"description": "For top: numeric/string path inside each selected item used for ordering."
},
"limit": {
"type": "number",
"description": "Max rows returned by top/concat/group reducers (default 10, max 100)."
}
},
"required": [
"op"
]
},
"description": "Named reductions to compute from subcall outputs. Example: {\"total\":{\"op\":\"sum\",\"path\":\"results[].picked\"},\"top\":{\"op\":\"top\",\"path\":\"results[]\",\"sortBy\":\"picked\",\"limit\":5}}."
},
"pipeline": {
"type": "array",
"maxItems": 64,
"description": "LINQ-style chained transforms over the raw batch result. Each step feeds the next. Ops: from, expand, where, select/project, groupBy, orderBy/sort, take/limit, skip, distinct, count, sum, avg, min, max, first, top. Example: [{\"op\":\"from\",\"path\":\"results[]\"},{\"op\":\"expand\",\"path\":\"output.programs[]\"},{\"op\":\"where\",\"path\":\"type\",\"in\":[\"token\",\"canonical-token\"]},{\"op\":\"groupBy\",\"by\":\"_chain\",\"as\":\"chain\",\"aggregates\":{\"tokens\":{\"op\":\"count\"},\"activity\":{\"op\":\"sum\",\"path\":\"activity\"}}},{\"op\":\"orderBy\",\"path\":\"tokens\",\"dir\":\"desc\"},{\"op\":\"take\",\"count\":5}].",
"items": {
"type": "object",
"additionalProperties": true,
"properties": {
"op": {
"type": "string",
"description": "from | expand | where | select | project | groupBy | orderBy | sort | take | limit | skip | distinct | count | sum | avg | min | max | first | top"
},
"path": {
"type": "string",
"description": "Dot path. [] flattens arrays. \"$\" or \".\" means the current item."
},
"by": {
"type": "string",
"description": "groupBy/distinct key path."
},
"fields": {
"type": "object",
"additionalProperties": true,
"description": "Projection map: outputField -> input path. Use {\"literal\":value} for literal strings."
},
"aggregates": {
"type": "object",
"additionalProperties": true,
"description": "groupBy aggregates: name -> {op,path?}; ops: count, sum, avg, min, max, first, top."
},
"dir": {
"type": "string",
"description": "asc or desc for orderBy/top."
},
"count": {
"type": "number",
"description": "take/limit/top count."
},
"limit": {
"type": "number",
"description": "Alias for count."
}
},
"required": [
"op"
]
}
},
"linq": {
"type": "string",
"description": "LINQ-like query string compiled into pipeline steps. Supports fluent dot chaining and query clauses. .where()/.map()/.select() bodies AND .orderBy()/.orderByDesc()/.distinctBy()/.groupBy() keys are all real expressions — ternaries, &&/||, comparisons, arithmetic, member/index access, object/array literals, and a small method whitelist (.includes/.startsWith/.endsWith/.toLowerCase/.toUpperCase/.trim/.slice/.indexOf/.split/.join, Math.min/max/round/floor/ceil/abs, String()/Number()/Boolean()) all work, e.g. results.map(r => r.ok ? ({chain: r.id, height: r.output}) : ({chain: r.id, height: -1})), or ranking by a COMPUTED score: results.where(r => r.ok).orderByDesc(r => r.output.volume24h * r.output.priceChangePct).take(10) — the ranking key is not limited to a bare field. Fluent example: results.selectMany(r => r.output.programs[]).where(p => p.type in (\"token\",\"canonical-token\")).groupBy(p => p._chain, assets=count(), activity=sum(activity)).orderByDesc(assets).take(5). Clause example: from results[] | expand output.programs[] | where type in (\"token\",\"canonical-token\") | group by _chain as chain select assets=count(), activity=sum(activity) | order by assets desc | take 5."
},
"concurrency": {
"type": "number",
"description": "Parallelism for subcalls (default 8, max 12).",
"default": 8
},
"ignoreFailures": {
"type": "boolean",
"default": false,
"description": "When reduce/pipeline/linq is used, a failed subcall is normally still reported in `failures` alongside the aggregate result, since a `.where(ok)`-style query would otherwise make it invisible. Set true to suppress that and get back only {reductions?, result?} — use when you already expect some chains/calls to fail and only want whatever succeeded. Defaults to false (failures still shown) because silently dropping an error is a real information loss, not just an efficiency choice — this one is opt-in on purpose."
}
},
"required": [
"calls"
]
}Output Schema
{
"type": "object",
"properties": {
"ok": {
"type": "boolean",
"description": "omitted when reduce/pipeline/linq was requested — the aggregation response is just the answer, not this batch-fanout shape"
},
"calls": {
"type": "integer",
"description": "number of subcalls attempted; omitted when reduce/pipeline/linq was requested"
},
"concurrency": {
"type": "integer",
"description": "omitted when reduce/pipeline/linq was requested"
},
"results": {
"type": "array",
"items": {
"type": "object",
"description": "per-call result: id, tool, ok, picked/output or error"
},
"description": "omitted when reduce/pipeline/linq was requested — see failures instead for what went wrong"
},
"reductions": {
"type": "object",
"description": "named reducer outputs; omitted when args.reduce was not passed"
},
"result": {
"description": "The pipeline/linq output value — the entire point of the call when args.pipeline or args.linq was passed, returned alone rather than wrapped; omitted when neither was passed"
},
"failures": {
"type": "array",
"items": {
"type": "object",
"description": "failed subcall: id, tool, error"
},
"description": "omitted when every subcall succeeded, when ignoreFailures:true was passed, or when no aggregation was requested (failures show inside results instead)"
},
"note": {
"type": "string",
"description": "omitted when reduce/pipeline/linq was requested"
}
},
"required": []
}⚪bridge_quote(fromChain, toChain, fromToken, toToken, fromAmount, ...)
Bridge/swap ANY asset across ANY chain via LI.FI (the engine behind Jumper) — e.g. Arbitrum USDC → Robinhood Chain (4663) USDG, or bridge into ETH for gas. Returns the best route (estimated output, fees, bridge used, duration) PLUS an unsigned transactionRequest (to/data/value/gasLimit) that the CALLER signs and submits on the fromChain — no keys are held here. Chains by id or key (1 Ethereum, 42161 Arbitrum, 8453 Base, 10 Optimism, 137 Polygon, 999 HyperEVM, 4663 Robinhood Chain). Tokens by symbol or 0x address.
Input Schema
{
"type": "object",
"properties": {
"fromChain": {
"type": "string",
"description": "Source chain id or key, e.g. 42161 or ARB"
},
"toChain": {
"type": "string",
"description": "Destination chain id or key, e.g. 4663 (Robinhood Chain)"
},
"fromToken": {
"type": "string",
"description": "Source token symbol or 0x address, e.g. USDC"
},
"toToken": {
"type": "string",
"description": "Destination token symbol or 0x address, e.g. USDG or ETH"
},
"fromAmount": {
"type": "string",
"description": "Amount in the source token's smallest unit (e.g. 1000000 = 1 USDC at 6 decimals)"
},
"fromAddress": {
"type": "string",
"description": "Sender 0x address on the source chain"
},
"toAddress": {
"type": "string",
"description": "Recipient on the destination chain (defaults to fromAddress)"
}
},
"required": [
"fromChain",
"toChain",
"fromToken",
"toToken",
"fromAmount",
"fromAddress"
]
}Output Schema
{
"type": "object",
"properties": {
"bridge": {
"type": "string",
"description": "bridge tool used (e.g. across)"
},
"fromToken": {
"type": "string"
},
"toToken": {
"type": "string"
},
"fromChainId": {
"type": "integer"
},
"toChainId": {
"type": "integer"
},
"fromTokenAddress": {
"type": "string"
},
"toTokenAddress": {
"type": "string"
},
"fromAddress": {
"type": "string"
},
"toAddress": {
"type": "string"
},
"fromAmount": {
"type": "string"
},
"toAmount": {
"type": "string"
},
"toAmountMin": {
"type": "string"
},
"estimatedDurationSec": {
"type": "number"
},
"gasCostUsd": {
"type": "number"
},
"feeCostUsd": {
"type": "number"
},
"transactionRequest": {
"type": "object",
"description": "UNSIGNED tx (to, data, value, gasLimit) — caller signs & submits on the fromChain"
},
"note": {
"type": "string"
}
},
"required": [
"bridge",
"toAmount",
"transactionRequest"
]
}⚪bridge_status(txHash, bridge, fromChain, toChain)
Track a cross-chain bridge submitted via bridge_quote — returns DONE / PENDING / FAILED plus the receiving-chain tx once it completes. Pass the source-chain tx hash (and the bridge tool from the quote for a faster lookup).
Input Schema
{
"type": "object",
"properties": {
"txHash": {
"type": "string",
"description": "Source-chain transaction hash from submitting the bridge tx"
},
"bridge": {
"type": "string",
"description": "The bridge tool from bridge_quote (e.g. across, stargate) — optional"
},
"fromChain": {
"type": "string",
"description": "Source chain id/key (optional)"
},
"toChain": {
"type": "string",
"description": "Destination chain id/key (optional)"
}
},
"required": [
"txHash"
]
}Output Schema
{
"type": "object",
"properties": {
"status": {
"type": "string",
"description": "DONE | PENDING | FAILED | NOT_FOUND"
},
"substatus": {
"type": "string"
},
"substatusMessage": {
"type": "string"
},
"sending": {
"type": "object",
"description": "source-chain leg"
},
"receiving": {
"type": "object",
"description": "destination-chain leg (tx hash once complete)"
}
},
"required": [
"status"
]
}🟢hl_info(type, coin, user, rankBy, limit, ...)
Query the Hyperliquid Info API — the perps/spot order-book data layer (read-only, no auth). The 'type' field selects the query: meta (perps universe + leverage), l2Book (order book for a coin), allMids (mid prices), clearinghouseState (a user's positions/margin), spotMeta, meta+assetCtxs (mark/funding/OI), candleSnapshot, and more. For type:metaAndAssetCtxs specifically: the raw response is TWO PARALLEL top-level arrays (universe names, asset contexts) correlated only by array position — do not try to read/scan it directly for '200+ coins' style questions (funding-rate outliers, biggest open interest, highest volume). Pass rankBy instead: it joins the two arrays server-side, sorts, and returns only the top N — the correct way to answer 'what has the highest/most extreme funding/OI/volume right now'.
Input Schema
{
"type": "object",
"properties": {
"type": {
"type": "string",
"description": "Info request type, e.g. meta, l2Book, allMids, clearinghouseState, metaAndAssetCtxs"
},
"coin": {
"type": "string",
"description": "Coin symbol for l2Book/candleSnapshot (e.g. BTC, ETH)"
},
"user": {
"type": "string",
"description": "0x address for user-scoped queries (clearinghouseState, openOrders, userFills)"
},
"rankBy": {
"type": "string",
"description": "type:metaAndAssetCtxs ONLY. One of funding | fundingAbs | openInterest | volume. Joins each coin's name to its funding/OI/volume, drops delisted coins, sorts, and returns {ranked, rankBy, dir, totalCoins} instead of the raw two-array response. Use fundingAbs for \"biggest funding outlier either direction\" (ranks by |funding|); use funding for \"most positive/most negative\" specifically (with dir)."
},
"limit": {
"type": "number",
"description": "rankBy only: how many ranked rows to return (default 20, max 100)"
},
"dir": {
"type": "string",
"description": "rankBy only: asc | desc (default desc — highest rankBy value first)"
},
"interval": {
"type": "string",
"description": "candleSnapshot only: candle interval, e.g. 1m,5m,15m,1h,4h,1d"
},
"startTime": {
"type": "number",
"description": "candleSnapshot only: start time epoch ms (default: endTime minus 500 intervals)"
},
"endTime": {
"type": "number",
"description": "candleSnapshot only: end time epoch ms (default: now)"
}
},
"required": [
"type"
]
}🟢api_get(path)
GET any public read endpoint of rpc.aex402.com: /health, /credits?wallet=, /pumpfun?limit=, /pumpfun/tuple?mint=, /security/<pool>, /market/list, /sniper/leaderboard, /sniper/bets?id=, /settlement/<sig>, /settlements/<wallet>, /ai/models, /ai/stats, /leaderboard, /openapi.json, /llms.txt, /rh/pools (Robinhood), /hl/pools (HyperEVM), /base/pools (Base Uniswap v3), /eth/pools (Ethereum Uniswap v3), /arb/pools (Arbitrum Uniswap v3)
Input Schema
{
"type": "object",
"properties": {
"path": {
"type": "string",
"description": "Endpoint path including query string, e.g. /security/9Wq.. or /pumpfun?limit=5"
}
},
"required": [
"path"
]
}🟢discover_programs(chain)
Discover on-chain programs/contracts across every chain this RPC supports (Solana, Slonana SVM, Robinhood, HyperEVM, Ethereum, Base, Stable, Plasma, Tempo, Codex). Returns a curated seed MERGED with programs/contracts AUTO-DISCOVERED from recent block activity (refreshed hourly) — each carries an `activity` count of recent invocations/calls; entries with type "discovered" were seen live on-chain but not yet named. Use this to learn what is actually active on-chain right now, then describe_program to introspect any specific address.
Input Schema
{
"type": "object",
"properties": {
"chain": {
"type": "string",
"description": "Filter to one chain: solana | slonana | robinhood | hyperevm | ethereum | base | stable | plasma | tempo | codex. Omit or \"all\" for every chain.",
"default": "all"
}
}
}Output Schema
{
"type": "object",
"properties": {
"chain": {
"type": "string"
},
"count": {
"type": "integer"
},
"discovered": {
"type": "integer",
"description": "auto-discovered (not curated) entries"
},
"tokens": {
"type": "integer",
"description": "token contracts seen alongside programs"
},
"coverage": {
"type": [
"string",
"object"
],
"description": "what this scan enumerated: a string on the single-chain response, the full per-chain map on the all-chains response"
},
"note": {
"type": "string",
"description": "caveats about what this scan did and did not see"
},
"programs": {
"type": [
"array",
"object"
],
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "program/contract address"
},
"name": {
"type": "string"
},
"type": {
"type": "string",
"description": "'core' | 'curated' | 'discovered'"
},
"note": {
"type": "string"
},
"activity": {
"type": "integer",
"description": "recent invocations/calls"
}
},
"required": [
"id"
]
},
"description": "array on the single-chain response; a per-chain {chain: program[]} map on the all-chains response"
}
}
}🟢describe_program(chain, address)
Introspect ANY specific program/contract address on a chain. Solana/Slonana: returns executable, owner, data size, and whether it is a known program. EVM: RPC-verified facts (is-contract, code size, ERC-20 name/symbol/decimals, EIP-1967 proxy → implementation) PLUS Blockscout explorer enrichment when available.
Input Schema
{
"type": "object",
"properties": {
"chain": {
"type": "string",
"description": "solana | slonana | robinhood | hyperevm | ethereum | base | stable | plasma | tempo | codex"
},
"address": {
"type": "string",
"description": "Program id (base58, Solana/Slonana) or contract address (0x…, EVM)"
}
},
"required": [
"chain",
"address"
]
}Output Schema
{
"type": "object",
"properties": {
"chain": {
"type": "string"
},
"address": {
"type": "string"
},
"exists": {
"type": "boolean",
"description": "Solana/Slonana only — omitted when the chain is EVM (isContract is the EVM equivalent)"
},
"isProgram": {
"type": "boolean",
"description": "Solana/Slonana only — omitted when the chain is EVM"
},
"executable": {
"type": "boolean",
"description": "Solana/Slonana only — omitted when the chain is EVM"
},
"owner": {
"type": "string",
"description": "owning program. Solana/Slonana only — omitted when the chain is EVM"
},
"dataLen": {
"type": "integer",
"description": "account data length in bytes. Solana/Slonana only — omitted when the chain is EVM (codeSize is the EVM equivalent)"
},
"lamports": {
"type": "integer",
"description": "Solana/Slonana only — omitted when the chain is EVM"
},
"isContract": {
"type": "boolean",
"description": "EVM only — omitted when the chain is Solana/Slonana, where executable/isProgram carry this instead"
},
"codeSize": {
"type": "integer",
"description": "EVM bytecode length in bytes. EVM only — omitted when the chain is Solana/Slonana (dataLen is the Solana equivalent)"
},
"erc20": {
"type": "object",
"description": "ERC-20 name/symbol/decimals. EVM only — omitted when the address is not an ERC-20, or the chain is Solana/Slonana"
},
"proxy": {
"type": "object",
"description": "EIP-1967 proxy standard + implementation. EVM only — omitted when the address is not a proxy, or the chain is Solana/Slonana"
},
"known": {
"type": [
"object",
"null"
],
"description": "curated registry entry {id,name,type,note} when the address is recognised"
}
},
"required": [
"chain",
"address"
]
}⚪reconstruct_abi(chain, address)
Reconstruct a PARTIAL function/event interface for an EVM contract on a supported EVM chain from its BYTECODE — no source or verification needed. Extracts PUSH4 function selectors + recent event topic0 hashes and resolves the ones public signature DBs (openchain/4byte) know to human signatures. Works on UNVERIFIED contracts because bytecode is ground truth, but it is NOT a full ABI: novel/proprietary selectors DBs have never seen stay unresolved (decompile for those). Use it to understand what an unknown contract does before trusting behavior-based guesses.
Input Schema
{
"type": "object",
"properties": {
"chain": {
"type": "string",
"description": "robinhood | hyperevm | ethereum | base | stable | plasma | tempo | codex"
},
"address": {
"type": "string",
"description": "EVM contract address (0x…). For a proxy, pass the implementation for the real logic."
}
},
"required": [
"chain",
"address"
]
}Output Schema
{
"type": "object",
"properties": {
"chain": {
"type": "string"
},
"address": {
"type": "string"
},
"isContract": {
"type": "boolean"
},
"codeSize": {
"type": "integer"
},
"functionCount": {
"type": "integer",
"description": "total PUSH4 selectors found"
},
"functions": {
"type": "array",
"items": {
"type": "object",
"description": "{selector, sig}"
},
"description": "resolved function signatures"
},
"unresolvedSelectors": {
"type": "array",
"items": {
"type": "string"
},
"description": "novel/proprietary selectors no DB knows"
},
"events": {
"type": "array",
"items": {
"type": "object",
"description": "{topic0, sig}"
},
"description": "resolved event signatures"
},
"note": {
"type": "string",
"description": "what the reconstruction could and could not resolve"
}
},
"required": [
"chain",
"address",
"isContract"
]
}🟢search_tokens(query, chain, limit)
Search the live token/NFT census for Robinhood Chain (4663) and HyperEVM (999) by symbol or name. Returns matching tokens with address, standard (erc20/erc721/erc1155), decimals, holders, market cap, and — for HyperEVM canonical tokens — live spot price + 24h volume. The census is refreshed hourly (canonical tokens from Hyperliquid spotMeta, top tokens from Blockscout, spam-filtered). Use this instead of discover_programs when you want a specific asset (e.g. "USDC on hyperevm", "stablecoins on robinhood") rather than the whole list.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Symbol or name substring, case-insensitive (e.g. \"usdc\", \"hype\"). Omit to list the top of the census."
},
"chain": {
"type": "string",
"description": "robinhood | hyperevm. Omit to search both."
},
"limit": {
"type": "number",
"description": "Max results (default 20).",
"default": 20
}
}
}Output Schema
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"chains": {
"type": "array",
"items": {
"type": "string"
}
},
"count": {
"type": "integer"
},
"censusAgeMin": {
"type": "number",
"description": "minutes since the census cron last ran"
},
"tokens": {
"type": "array",
"items": {
"type": "object",
"description": "address, symbol, name, standard, decimals, holders, marketCap, price"
}
},
"note": {
"type": "string"
}
},
"required": [
"count",
"tokens"
]
}🟢discovery_health
Report the freshness and health of the cross-chain program/token discovery pipeline: when the hourly cron last ran, how many programs/tokens each chain scan produced, and which scans failed. Use this to check whether discover_programs / search_tokens data is current before relying on it.
Input Schema
{
"type": "object",
"properties": {}
}Output Schema
{
"type": "object",
"properties": {
"status": {
"type": "string",
"description": "healthy | stale | degraded"
},
"lastRunAgeMin": {
"type": "number"
},
"lastRunUnix": {
"type": "integer"
},
"counts": {
"type": "object",
"description": "per-chain program counts from the last scan"
},
"history": {
"type": "array",
"items": {
"type": "object",
"properties": {
"ts": {
"type": "integer",
"description": "unix seconds"
},
"counts": {
"type": "object",
"description": "per-chain program count at that run"
}
}
},
"description": "per-chain counts over the last <=24 cron runs, oldest first"
},
"failedScans": {
"type": "array",
"items": {
"type": "string"
},
"description": "chains whose last scan errored (omitted when none)"
},
"emptyScans": {
"type": "array",
"items": {
"type": "string"
},
"description": "chains whose last scan returned zero (omitted when none)"
},
"sourceErrors": {
"type": "object",
"description": "per-chain list of what each live source ACTUALLY answered when it failed, e.g. \"robinhood/ERC-20: blockscout /api/v2/tokens → 403\". Says WHY a census is thin where seedsOnlyScans only says THAT it is. Capped at 4 entries per chain; when more were recorded the list carries a final \"… +N more (T total)\" string, so the count survives the truncation rather than the list silently reading as complete. Omitted when every source succeeded"
},
"seedsOnlyScans": {
"type": "array",
"items": {
"type": "string"
},
"description": "chains whose last scan returned ONLY hardcoded canonical seeds — every live source returned nothing while the fallback held, so the count is non-zero and emptyScans does NOT list them. Sets status=degraded. Omitted when none"
},
"censusLiveRecords": {
"type": "object",
"description": "per-census count of records the LIVE source returned, before any merge, cap or spam filter — the evidence behind seedsOnlyScans. 0 means the live source supplied nothing (the census is its fallback); -1 means this census was last written by a build that did not record the field, which is NOT the same as zero. Published even when healthy, so a reader can distinguish \"source is fine\" from \"nothing was measured\" without inferring it from a verdict. Never omitted: built over the census keys in counts, so every census always carries a value and -1 covers the pre-field case — the earlier exemption for records predating the field was retired when the conditional spread was removed"
},
"censusRecordsBeforeCap": {
"type": "object",
"description": "per-census record count BEFORE the fungible (170) and NFT (50) caps. A count sitting exactly on its cap cannot say whether it is a finding or a ceiling — hyperevm_census reads 170 because 170 IS the cap. Compare against counts: a value here greater than the published count means that census was TRUNCATED, equal means it was not. -1 means the build that last wrote this census did not record the field. Never omitted, same construction as censusLiveRecords"
},
"note": {
"type": "string",
"description": "plain-language reading of status"
}
},
"required": [
"status"
]
}⚪payment_help
How to pay for API access (x402 micropayments) — the complete self-serve guide for agents: current prices, every accepted asset/chain (USDC/USDT/SOL/ANSEM on Solana, ETH/USDG on Robinhood Chain, USDC/HYPE on HyperEVM), the merchant addresses, step-by-step topup → session-token → API-key flow, and how to attach credentials to MCP calls. This tool is FREE and NEVER rate-limited — call it when you hit a 402 / rate limit to convert into a paid session ($0.01 minimum buys 100 calls, no signup).
Input Schema
{
"type": "object",
"properties": {}
}Output Schema
{
"type": "object",
"properties": {
"freeTier": {
"type": "object",
"additionalProperties": true
},
"paidTier": {
"type": "object",
"additionalProperties": true,
"description": "Prices, accepted assets with mints/contracts + merchant addresses, howToPay steps"
},
"quickstart": {
"type": "object",
"additionalProperties": true
},
"mcp": {
"type": "object",
"additionalProperties": true,
"description": "MCP-specific: which methods stay free, how to attach X-Session / Bearer key to MCP requests"
},
"docs": {
"type": "string"
},
"note": {
"type": "string",
"description": "one-line summary of the cheapest path to a paid session"
}
},
"required": [
"paidTier",
"mcp",
"docs"
]
}🟢search(query)
Search the aeX402 universe by keyword: tokens (Robinhood Chain + HyperEVM census), known programs/contracts (Solana, Robinhood, HyperEVM, Slonana), and live AeX402 AMM pools. Returns a result list; pass a result id to the fetch tool for full detail. Use the specialist tools (search_tokens, discover_programs, aex402_listPools) when you already know the entity type.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Keyword: token symbol/name (\"usdg\"), program name (\"pump.fun\"), contract address, or pool address."
}
},
"required": [
"query"
]
}Output Schema
{
"type": "object",
"properties": {
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Opaque id for fetch: token:<chain>:<address> | program:<chain>:<address> | pool:<address>"
},
"title": {
"type": "string"
},
"url": {
"type": "string"
}
},
"required": [
"id",
"title",
"url"
]
}
}
},
"required": [
"results"
]
}🟢fetch(id)
Fetch the full document for one search result id (from the search tool). Accepts token:<chain>:<address>, program:<chain>:<address>, or pool:<address>. Returns the entity detail (on-chain state for pools, census entry for tokens, registry/introspection for programs) as a document.
Input Schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "A search result id, e.g. \"pool:G5d3qFZq...\" or \"token:robinhood:0x5fc5...\" or \"program:solana:3AMM53...\""
}
},
"required": [
"id"
]
}Output Schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"text": {
"type": "string",
"description": "Entity detail as pretty-printed JSON/prose"
},
"url": {
"type": "string"
},
"metadata": {
"type": "object",
"additionalProperties": true
}
},
"required": [
"id",
"title",
"text",
"url"
]
}Community
Evidence