{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"smithery_agentfi-agentfi-defi","slug":"agentfi-agentfi-defi","name":"AgentFi — DeFi Tools for AI Agents","type":"mcp","url":"https://github.com/felippeyann/agentfi","page_url":"https://unfragile.ai/agentfi-agentfi-defi","categories":["mcp-servers"],"tags":["mcp","model-context-protocol","smithery:agentfi/agentfi-defi"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"smithery_agentfi-agentfi-defi__cap_0","uri":"capability://tool.use.integration.evm.token.swap.execution.with.pre.broadcast.simulation","name":"evm token swap execution with pre-broadcast simulation","description":"Executes token swaps across EVM chains (Ethereum, Base, Arbitrum, Polygon) by constructing swap transactions through DEX aggregator integration, simulating execution on-chain via eth_call to validate slippage and gas costs before broadcasting to the network. Uses Safe smart wallet as execution context with MPC key management via Turnkey, ensuring swaps are policy-constrained and reversible until final broadcast.","intents":["I want my agent to swap tokens autonomously while preventing slippage beyond a threshold","I need to test a swap transaction before committing it to the blockchain","I want swap execution to be auditable and constrained by predefined policies"],"best_for":["AI agents managing treasury or yield strategies","DeFi protocol developers building autonomous market-making agents","Teams requiring auditable, policy-constrained token exchanges"],"limitations":["Simulation accuracy depends on DEX liquidity state at simulation time; MEV and front-running not modeled in pre-broadcast simulation","Slippage constraints are enforced at simulation time only; actual execution may differ if mempool conditions change between simulation and broadcast","Limited to EVM chains; no support for Solana, Cosmos, or other VM architectures"],"requires":["EVM RPC endpoint (Infura, Alchemy, or self-hosted)","Turnkey API key for MPC key management","Safe smart wallet deployed on target chain","Sufficient gas balance in agent wallet"],"input_types":["token addresses (ERC-20 contract addresses)","swap amounts (wei or decimal format)","slippage tolerance (basis points or percentage)","chain identifier (chainId)"],"output_types":["transaction hash (0x-prefixed hex)","simulated swap output amount","gas estimate (wei)","execution status (pending/confirmed/failed)"],"categories":["tool-use-integration","defi-execution"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_agentfi-agentfi-defi__cap_1","uri":"capability://data.processing.analysis.multi.chain.asset.balance.and.price.querying","name":"multi-chain asset balance and price querying","description":"Queries real-time token balances and market prices across EVM chains by calling ERC-20 balanceOf() for on-chain state and integrating with price oracles (Chainlink, Uniswap TWAP, or DEX spot prices) to return current portfolio value. Caches price data with configurable TTL to reduce oracle calls and RPC load, returning structured balance/price tuples for agent decision-making.","intents":["I want my agent to check its current wallet balance before executing a trade","I need real-time token prices to calculate portfolio value and rebalancing thresholds","I want to query multiple token balances in a single call to reduce RPC overhead"],"best_for":["Portfolio monitoring agents that need sub-second balance updates","Yield farming bots calculating APY and rebalancing triggers","Risk management systems enforcing position size limits"],"limitations":["Price data freshness depends on oracle update frequency; Chainlink feeds update every 1-24 hours depending on asset volatility","Spot price queries may not reflect true execution price due to slippage on illiquid pairs","Cache TTL creates stale price windows; aggressive caching (< 5 seconds) increases RPC costs"],"requires":["EVM RPC endpoint with eth_call support","Price oracle integration (Chainlink, Uniswap V3 TWAP, or DEX router)","Token contract addresses (ERC-20 standard)","Agent wallet address on target chain"],"input_types":["token addresses (ERC-20 contract addresses)","wallet address (0x-prefixed)","chain identifier (chainId)","optional: price oracle preference (chainlink/uniswap/dex)"],"output_types":["balance amount (wei or decimal)","token price (USD or base asset)","total portfolio value (USD equivalent)","price timestamp (unix epoch)"],"categories":["data-processing-analysis","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_agentfi-agentfi-defi__cap_10","uri":"capability://tool.use.integration.transaction.simulation.and.dry.run.execution","name":"transaction simulation and dry-run execution","description":"Simulates pending transactions using eth_call RPC method to execute transactions in a read-only mode, returning the expected output (swap amounts, collateral ratios, transfer status, etc.) without modifying blockchain state. Detects transaction failures (reverts, out-of-gas, insufficient balance) before broadcast, and provides detailed error messages to help agents understand why transactions would fail. Integrates with all DeFi operations to provide pre-broadcast validation.","intents":["I want to validate my agent's transaction before broadcasting to avoid wasting gas on failed transactions","I need to check if a swap will succeed and what output amount I'll receive before committing","I want to detect transaction failures early and adjust parameters (e.g., slippage) before broadcast"],"best_for":["Agents executing complex DeFi transactions with multiple dependencies","Builders implementing agent retry logic with parameter adjustment","Teams with strict gas budgets where failed transactions are costly"],"limitations":["Simulation accuracy depends on RPC node state; may diverge from actual execution if mempool conditions change","Simulations do not account for MEV or transaction ordering; actual execution may differ","Simulation gas estimates include buffer but may underestimate during network congestion","Some contract behaviors (e.g., randomness, external calls) cannot be simulated accurately"],"requires":["EVM RPC endpoint with eth_call support","Transaction data (to, from, data, value)","Optional: state overrides (for testing with hypothetical state changes)"],"input_types":["transaction object (to, from, data, value)","chain identifier (chainId)","block number (optional, for historical simulation)"],"output_types":["simulation result (success or failure)","return data (decoded output from contract call)","gas estimate (gas that would be consumed)","error message (if simulation failed, with revert reason)"],"categories":["tool-use-integration","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_agentfi-agentfi-defi__cap_2","uri":"capability://tool.use.integration.aave.lending.protocol.interaction.with.collateral.management","name":"aave lending protocol interaction with collateral management","description":"Supplies ERC-20 tokens to Aave lending pools and manages collateral by calling Aave V3 contract functions (supply, withdraw, borrow, repay) through Safe smart wallet. Validates collateral ratios and liquidation thresholds before execution via simulation, preventing over-leveraged positions. Tracks aToken balances and interest accrual to enable yield farming strategies.","intents":["I want my agent to deposit tokens into Aave and earn lending interest","I need to check my collateral ratio before borrowing against my deposits","I want my agent to repay debt automatically when interest accrues above a threshold"],"best_for":["Yield farming agents optimizing lending APY across protocols","Leveraged trading bots managing collateral and debt positions","Treasury management agents earning passive yield on idle assets"],"limitations":["Collateral ratio validation is point-in-time; liquidation risk increases if collateral price drops between validation and execution","Interest accrual is asynchronous; agent cannot directly trigger interest calculation — must wait for Aave's internal accounting updates","Aave V3 has supply/borrow caps per asset; transactions may fail if pool capacity is exhausted"],"requires":["Aave V3 deployment on target EVM chain (Ethereum, Arbitrum, Polygon, Base, Optimism)","ERC-20 token approved for Aave LendingPool contract","Safe smart wallet with sufficient gas balance","RPC endpoint with eth_call for simulation"],"input_types":["token address (ERC-20 contract)","amount (wei)","action type (supply/withdraw/borrow/repay)","optional: max slippage for interest rate swaps"],"output_types":["aToken balance (wei)","collateral ratio (percentage)","liquidation threshold (percentage)","transaction hash (0x-prefixed)"],"categories":["tool-use-integration","defi-execution"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_agentfi-agentfi-defi__cap_3","uri":"capability://safety.moderation.policy.constrained.transaction.execution.with.approval.workflows","name":"policy-constrained transaction execution with approval workflows","description":"Enforces agent-specific transaction policies (spending limits, token whitelists, counterparty restrictions) by validating each transaction against a policy rule engine before Safe smart wallet execution. Policies are defined as JSON schemas and evaluated server-side; transactions violating policies are rejected before broadcast. Supports approval workflows where high-value transactions require human or oracle confirmation.","intents":["I want to limit my agent's daily spending to prevent runaway losses","I need to whitelist specific tokens and prevent my agent from trading unknown assets","I want high-value transactions to require manual approval before execution"],"best_for":["Risk-averse teams deploying autonomous agents with bounded loss exposure","Enterprises requiring audit trails and approval workflows for agent transactions","Multi-agent systems where parent agents control child agent spending"],"limitations":["Policy evaluation is synchronous; complex rule engines add 50-200ms latency per transaction","Policies are static at agent creation time; dynamic policy updates require agent restart or external state management","Approval workflows introduce human-in-the-loop delays; high-frequency trading strategies cannot use approval gates"],"requires":["Policy definition in JSON schema format","Safe smart wallet with policy enforcement contract deployed","Approval oracle or human reviewer endpoint (for approval workflows)","Policy rule engine (built-in or custom)"],"input_types":["policy rules (JSON schema with spending limits, token whitelists, counterparty restrictions)","transaction data (to/from, amount, token, function signature)","optional: approval request metadata (reason, requester)"],"output_types":["policy validation result (approved/rejected)","rejection reason (if applicable)","approval request ID (if approval workflow triggered)","transaction hash (after approval)"],"categories":["safety-moderation","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_agentfi-agentfi-defi__cap_4","uri":"capability://tool.use.integration.safe.smart.wallet.provisioning.with.mpc.key.management.via.turnkey","name":"safe smart wallet provisioning with mpc key management via turnkey","description":"Provisions a dedicated Safe smart wallet for each agent by deploying a Safe proxy contract and registering MPC-managed keys via Turnkey's key management service. Turnkey handles key generation, signing, and rotation without exposing private keys to the application layer. Each agent receives a unique wallet address and can execute transactions through Safe's multi-sig interface with MPC-backed signatures.","intents":["I want to give my agent a non-custodial wallet without managing private keys myself","I need key rotation and secure key storage for long-running agents","I want to revoke agent wallet access without redeploying the agent"],"best_for":["Production AI agents requiring institutional-grade key security","Multi-agent systems where each agent needs isolated wallet credentials","Compliance-heavy environments requiring key audit trails and rotation policies"],"limitations":["Turnkey API calls add 200-500ms latency per transaction signing operation","Safe wallet deployment requires gas payment; initial setup costs ~$50-200 depending on network congestion","MPC key recovery is complex; if Turnkey service is unavailable, agent cannot sign transactions until service recovers"],"requires":["Turnkey API key and organization ID","EVM RPC endpoint for Safe contract deployment","Gas balance in deployment account (0.1-0.5 ETH equivalent)","Safe contract factory deployed on target chain (standard Safe deployment)"],"input_types":["agent identifier (unique string)","chain identifier (chainId)","optional: Safe configuration (threshold, owners, delay)"],"output_types":["wallet address (0x-prefixed Safe proxy)","Turnkey key ID (for signing operations)","deployment transaction hash","wallet initialization status"],"categories":["tool-use-integration","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_agentfi-agentfi-defi__cap_5","uri":"capability://tool.use.integration.asset.transfer.with.recipient.validation.and.memo.support","name":"asset transfer with recipient validation and memo support","description":"Transfers ERC-20 tokens or native chain assets (ETH, MATIC, ARB) from agent wallet to recipient addresses via Safe smart wallet, with optional recipient validation (checking if address is a contract, known exchange, or whitelisted address) and memo/note attachment for transaction tracking. Validates recipient address format and checks for common mistakes (sending to token contract address, zero address).","intents":["I want my agent to send tokens to a user wallet with a memo explaining the transfer","I need to prevent my agent from accidentally sending funds to invalid addresses","I want to validate that a recipient address is a legitimate wallet before transfer"],"best_for":["Reward distribution agents paying out tokens to users","Treasury management agents distributing funds across wallets","Automated refund systems processing user withdrawals"],"limitations":["Recipient validation is heuristic-based; cannot definitively determine if an address is legitimate without external oracle","Memo is stored off-chain or in transaction calldata; not queryable from blockchain directly","No built-in support for conditional transfers (e.g., transfer only if recipient has verified identity)"],"requires":["Safe smart wallet with sufficient balance","Recipient address (0x-prefixed Ethereum address)","EVM RPC endpoint for address validation","Optional: recipient whitelist or validation oracle"],"input_types":["recipient address (0x-prefixed)","amount (wei or decimal)","token address (0x0000... for native asset, ERC-20 address for tokens)","optional: memo/note (string, max 256 characters)"],"output_types":["transaction hash (0x-prefixed)","recipient validation result (valid/warning/error)","transfer status (pending/confirmed/failed)","transaction receipt (block number, gas used)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_agentfi-agentfi-defi__cap_6","uri":"capability://tool.use.integration.mcp.tool.schema.registration.and.function.calling.interface","name":"mcp tool schema registration and function calling interface","description":"Exposes DeFi capabilities as MCP (Model Context Protocol) tools with JSON schema definitions, allowing LLM agents to discover and invoke DeFi functions through standard MCP function-calling interface. Each tool includes input/output schemas, descriptions, and error handling. Agent can call tools via MCP client library, which handles schema validation, parameter marshalling, and response parsing.","intents":["I want my LLM agent to discover available DeFi operations without hardcoding function names","I need my agent to validate transaction parameters against schemas before execution","I want to expose DeFi tools to multiple LLM providers (OpenAI, Anthropic, Claude) through a standard interface"],"best_for":["LLM-powered agents using OpenAI, Anthropic, or other MCP-compatible models","Multi-model agent systems requiring provider-agnostic tool interfaces","Teams building agent frameworks that need pluggable DeFi capabilities"],"limitations":["MCP schema validation adds 10-50ms overhead per tool call due to JSON schema parsing","Tool discovery is static; dynamic tool registration requires MCP server restart","Error handling is schema-based; complex error scenarios may not map cleanly to JSON schema validation errors"],"requires":["MCP client library (Python, Node.js, or language-specific implementation)","LLM provider with function-calling support (OpenAI, Anthropic, Ollama)","AgentFi MCP server running and accessible to client"],"input_types":["MCP tool call with parameters matching JSON schema","function name (string)","parameters (JSON object)"],"output_types":["tool result (JSON object matching output schema)","error message (if validation or execution fails)","execution metadata (gas estimate, simulation result)"],"categories":["tool-use-integration","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_agentfi-agentfi-defi__cap_7","uri":"capability://data.processing.analysis.transaction.simulation.and.gas.estimation.with.revert.reason.extraction","name":"transaction simulation and gas estimation with revert reason extraction","description":"Simulates transactions before broadcast using eth_call to predict execution outcomes, gas consumption, and failure modes. Extracts revert reasons from failed simulations by parsing contract error messages and ABI-decoded error data, providing agents with actionable failure diagnostics. Estimates gas costs based on simulation results and current network gas prices.","intents":["I want to test a transaction before sending it to avoid wasting gas on failed transactions","I need to understand why a transaction would fail so I can adjust parameters","I want accurate gas estimates to budget transaction costs"],"best_for":["Risk-averse agents that validate transactions before execution","Debugging tools for DeFi developers testing contract interactions","Gas optimization systems that need accurate cost estimates"],"limitations":["Simulation accuracy depends on state consistency; if state changes between simulation and execution, results may differ","Revert reason extraction requires ABI decoding; custom error types may not decode correctly without ABI","Gas estimates are point-in-time; network congestion changes between simulation and execution affect actual gas costs"],"requires":["EVM RPC endpoint with eth_call support","Transaction data (to, from, data, value)","Optional: contract ABI for error decoding","Current network gas price data"],"input_types":["transaction object (to, from, data, value, gas)","optional: contract ABI (for error decoding)","block number (for state consistency)"],"output_types":["simulation result (success/failure)","revert reason (string, if failed)","gas used (wei)","gas estimate (wei)","output data (if successful)"],"categories":["data-processing-analysis","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_agentfi-agentfi-defi__cap_8","uri":"capability://automation.workflow.multi.chain.transaction.orchestration.with.cross.chain.state.consistency","name":"multi-chain transaction orchestration with cross-chain state consistency","description":"Orchestrates transactions across multiple EVM chains (Ethereum, Base, Arbitrum, Polygon) by managing nonce sequences, gas price adjustments, and execution ordering to maintain state consistency. Handles transaction ordering to prevent race conditions (e.g., ensuring token approval completes before swap execution) and provides rollback mechanisms if a transaction fails mid-sequence.","intents":["I want my agent to execute a swap on Arbitrum and then bridge the output to Ethereum in a single coordinated operation","I need to ensure token approvals complete before swap execution across multiple chains","I want automatic rollback if a transaction fails in a multi-step sequence"],"best_for":["Cross-chain arbitrage agents executing trades on multiple networks","Portfolio rebalancing agents moving assets between chains","Yield farming agents optimizing returns across multiple protocols"],"limitations":["Cross-chain atomicity is not guaranteed; if a transaction succeeds on chain A but fails on chain B, manual intervention may be required","Bridge latency introduces delays; cross-chain transactions may take 10-60 minutes depending on bridge protocol","Nonce management is complex; if transactions are submitted out of order, later transactions may fail due to nonce gaps"],"requires":["RPC endpoints for all target chains","Safe smart wallet deployed on each chain","Bridge protocol integration (Stargate, Across, or native bridge)","Sufficient gas balance on each chain"],"input_types":["transaction sequence (array of transactions with chain IDs)","optional: rollback policy (all-or-nothing, best-effort)","optional: timeout per transaction"],"output_types":["transaction hashes per chain","execution status (pending/confirmed/failed)","rollback status (if applicable)","cross-chain state consistency report"],"categories":["automation-workflow","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_agentfi-agentfi-defi__cap_9","uri":"capability://automation.workflow.real.time.transaction.monitoring.and.event.tracking","name":"real-time transaction monitoring and event tracking","description":"Monitors on-chain transaction status and emits events as transactions progress through mempool, confirmation, and finality states. Tracks transaction receipts, logs, and state changes to provide agents with real-time execution feedback. Integrates with event listeners to trigger agent actions on transaction confirmation or failure (e.g., rebalance portfolio after swap confirms).","intents":["I want my agent to wait for a transaction to confirm before executing the next step","I need to track swap execution and update my portfolio state when the transaction confirms","I want to detect transaction failures and trigger automatic retry logic"],"best_for":["Sequential DeFi agents that depend on transaction confirmation before proceeding","Portfolio tracking systems that need real-time state updates","Automated retry systems that resubmit failed transactions"],"limitations":["Event tracking latency depends on RPC provider; some providers have 5-30 second delays in event emission","Mempool monitoring is not available on all RPC providers; some only expose confirmed transactions","Finality varies by chain; Ethereum requires ~12 minutes for finality, while Polygon is ~2 minutes"],"requires":["EVM RPC endpoint with event log support","WebSocket or polling-based event listener","Transaction hash to monitor","Optional: event filter (specific log topics or contract addresses)"],"input_types":["transaction hash (0x-prefixed)","optional: event filters (topics, addresses)","optional: confirmation threshold (number of blocks)"],"output_types":["transaction status (mempool/pending/confirmed/failed)","block number (when confirmed)","transaction receipt (gas used, logs)","event data (if applicable)"],"categories":["automation-workflow","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":38,"verified":false,"data_access_risk":"moderate","permissions":["EVM RPC endpoint (Infura, Alchemy, or self-hosted)","Turnkey API key for MPC key management","Safe smart wallet deployed on target chain","Sufficient gas balance in agent wallet","EVM RPC endpoint with eth_call support","Price oracle integration (Chainlink, Uniswap V3 TWAP, or DEX router)","Token contract addresses (ERC-20 standard)","Agent wallet address on target chain","Transaction data (to, from, data, value)","Optional: state overrides (for testing with hypothetical state changes)"],"failure_modes":["Simulation accuracy depends on DEX liquidity state at simulation time; MEV and front-running not modeled in pre-broadcast simulation","Slippage constraints are enforced at simulation time only; actual execution may differ if mempool conditions change between simulation and broadcast","Limited to EVM chains; no support for Solana, Cosmos, or other VM architectures","Price data freshness depends on oracle update frequency; Chainlink feeds update every 1-24 hours depending on asset volatility","Spot price queries may not reflect true execution price due to slippage on illiquid pairs","Cache TTL creates stale price windows; aggressive caching (< 5 seconds) increases RPC costs","Simulation accuracy depends on RPC node state; may diverge from actual execution if mempool conditions change","Simulations do not account for MEV or transaction ordering; actual execution may differ","Simulation gas estimates include buffer but may underestimate during network congestion","Some contract behaviors (e.g., randomness, external calls) cannot be simulated accurately","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.05,"quality":0.57,"ecosystem":0.48999999999999994,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.15,"match_graph":0.23,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:25.062Z","last_scraped_at":"2026-05-03T15:19:05.145Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=agentfi-agentfi-defi","compare_url":"https://unfragile.ai/compare?artifact=agentfi-agentfi-defi"}},"signature":"C3Bh/mrho/3xv86cNKbaA71B2HQdSzbjTSfZB3SWmwiyJ3J5dGg11cMWqohREZbWHHtDqxB1KR8YrpTJx7l+DQ==","signedAt":"2026-06-20T10:41:54.066Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/agentfi-agentfi-defi","artifact":"https://unfragile.ai/agentfi-agentfi-defi","verify":"https://unfragile.ai/api/v1/verify?slug=agentfi-agentfi-defi","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}