ChainRay

Get latest or specific block data including gas, transactions, and timestamps. Use for exact latest or historical block facts on one chain, including block number, gas, transactions, and timestamps. Do not use it for an aggregate chain health view; use chain.health for a single chain or oracle.chain_status for multi-chain status.

 ⟨13 unchanged words⟩ capital inflow (bullish) or outflow (bearish). Use for directional net capital flow across bridges on one chain. For large bridge-transfer detection, use chain.bridge.monitor; use chain.compare when choosing between chains.

 ⟨13 unchanged words⟩  yields. Helps choose the optimal chain for transactions. Use to compare a bounded set of EVM chains when selecting a network for an action. It is a decision aid, not an outage monitor or transaction executor; use chain.health for a single-chain snapshot, gas.tracker for a live fee quote, or oracle.chain_status for multi-chain status.

Chain health score aggregating gas data, protocol TVL, and stablecoin stability. Use for a single-chain operating snapshot before choosing where to act. The score is not a contract audit or a transaction guarantee; use security.contract.scan or token.risk for safety analysis and chain.block for block facts.

 ⟨13 unchanged words⟩  the best supply APY and cheapest borrow rates. Use for a cross-chain ranking of configured DeFi lending opportunities. For a chain-specific protocol comparison, use defi.compare; for one protocol's rates, use defi.yields.

 ⟨10 unchanged words⟩ frequency into a composite health score (0-100). Use for protocol-level DeFi health and stress signals on one chain. It does not rank yields or inspect a token contract; use defi.aggregator for cross-chain lending rankings, defi.compare for protocol rates, or token.risk for token risk.

 ⟨10 unchanged words⟩  price, active liquidity, fee tier. EVM only. Use when a known token pair needs pool-depth and active-liquidity context. It requires both token addresses and does not rank lending yields; use defi.aggregator or defi.compare for rates.

 ⟨11 unchanged words⟩ base fee per block. Solana: TPS performance samples. Scope: recent sampled fee history and trend. Use this for 'how have fees behaved recently?'. It is not a current quote (gas.tracker), a forecast (gas.predict), or a submission recommendation (gas.optimize).

 ⟨10 unchanged words⟩  the best time to transact. Includes savings estimate. Scope: read-only submission-timing advice derived from current and recent fee conditions. Use this for 'when should I submit?'. It is not the raw current quote (gas.tracker), a history response (gas.history), or a standalone forecast (gas.predict).

 ⟨13 unchanged words⟩  base fees. Returns prediction, trend, and recommendation. Scope: short-horizon fee forecast from recent samples. Use this for 'what may fees be soon?'. It is not a live quote (gas.tracker), historical data (gas.history), or a timing recommendation (gas.optimize), and it never executes a transaction.

 ⟨9 unchanged words⟩ predictions. Solana: priority fees, TPS, congestion level. Scope: current fee snapshot for a transaction decision. Use this for 'what are fees now?'. It is not a historical series (gas.history), a short-horizon forecast (gas.predict), or timing advice (gas.optimize).

Get recent DEX swap trades from a Uniswap V3 pool. Use for recent swaps in a known Uniswap V3 pool. It is pool-specific and read-only; use market.overview for a broad snapshot or defi.liquidity for pool state and depth.

 ⟨14 unchanged words⟩  Ethereum, Arbitrum, and Optimism in one call. Use for a fixed broad snapshot of major market, gas, and TVL signals. It is not a chain health verdict, token price lookup, or custom chain comparison; use chain.health, token.price, or chain.compare for those questions.

 ⟨12 unchanged words⟩  recommendations for ERC-7683 cross-chain intent execution. ($0.007) Use before evaluating an ERC-7683 cross-chain intent to compare gas, liquidity, competition, and estimated profitability. It does not execute the intent and should not be treated as a guaranteed quote; both source and destination must be supported EVM chains.

 ⟨12 unchanged words⟩  use watch-diff later to receive only changed fields. Use to create the first address snapshot in a stateful watch workflow. Save the returned watchId and call monitor.watch.diff in the same MCP session for later changes.

 ⟨8 unchanged words⟩  watched address. Returns changed fields and numeric deltas. Use only after monitor.watch.address has created a watchId in the same MCP session. It returns changes since the last check and advances the snapshot; create a new watch for a new address.

 ⟨11 unchanged words⟩ proxy patterns, ownership. No external APIs. EVM only. Scope: bytecode-level inspection of one EVM contract for proxy, ownership, delegatecall, and selfdestruct signals. Use this for 'what does the deployed code expose?'. It is not a token market/liquidity assessment (token.risk), a wallet score, or a full audit, and it does not judge a trade by itself.

 ⟨18 unchanged words⟩  agent should call this before swapping. ($0.05) Scope: composite pre-trade decision for a proposed swap, bridge, or liquidity action, focused on MEV exposure and slippage mitigation. Use this before acting. It is not a historical sandwich scan (security.sandwich), a token due-diligence report (token.risk), or a transaction executor.

 ⟨10 unchanged words⟩  Checks front-run + back-run patterns in surrounding transactions. Use to inspect historical sandwich patterns around an address. It is not a pre-trade protection decision; use security.mev.shield before a swap or liquidity action.

 ⟨11 unchanged words⟩  identify the largest net receivers of a token. Use for token-holder concentration and recent net accumulation. Do not use it for a wallet's portfolio or token price; use wallet.report for a wallet address or token.price for a token price.

 ⟨14 unchanged words⟩ Solana: checks mint/freeze authority, supply, Metaplex metadata. Scope: asset-level token due diligence for a token contract or mint, combining market, liquidity, verification, and control signals. Use this when the question is 'is this token safe or liquid?'. It is not raw bytecode inspection (use security.contract.scan), a wallet's financial behavior (use wallet.credit_score), or a multi-signal address dashboard (use analyze.risk_dashboard).

 ⟨5 unchanged words⟩  decimals, symbol, and name from on-chain data. Use for contract-level supply metadata such as total supply, decimals, symbol, and name. It does not assess price, token safety, or holder concentration; use token.risk, token.price, or token.holders instead.

 ⟨29 unchanged words⟩  signals). No LLM cost — pure data. Use at the start of a swap, bridge, invest, monitor, or general workflow to collect the relevant signals in one structured brief. Use focused tools when the agent already knows the exact data it needs.

 ⟨27 unchanged words⟩  use the paid HTTP API for per-request settlement. Use when the agent has a natural-language data question and needs ChainRay to select a focused route. For deterministic workflows, call the specific tool directly; paid HTTP requests are separate from this MCP capacity policy.

 ⟨22 unchanged words⟩  Use this tool to learn how to connect. Use to discover the five real-time SSE streams and their connection requirements. The returned guidance is not a stream itself; connect directly over HTTP with the documented Accept and payment headers.

 ⟨13 unchanged words⟩  verify that the data was produced by ChainRay. Use after receiving a ChainRay response with _proof.dataHash to verify its integrity. It verifies a supplied hash and does not independently validate the underlying blockchain data.

 ⟨18 unchanged words⟩ DeFi activity. Returns grade (AAA to C). Scope: wallet-level financial behavior and activity score based on transaction history, balances, token diversity, stablecoins, and DeFi use. Use this for 'how active or creditworthy is this wallet?'. It is not Agent identity/reputation (agent.reputation), a registered card (agent.card.lookup), or token/contract risk.