ToolTrust
A2/100
Smithery

li-fi-lifi-mcp

mcpsmithery

@Smithery

Cross-chain swaps, bridging, and DeFi yield discovery via the LI.FI aggregator. Provides MCP tools for quotes, routes, token and chain metadata, transaction status, ERC20 allowances, and yield vaults across 58 chains, 27+ bridges, and 31+ DEXes. Read-only — returns unsigned transaction requests for the agent's wallet to sign and broadcast. An optional LI.FI API key (Bearer or X-LiFi-Api-Key header) unlocks higher rate limits.

By Smithery | 74 findings | Scanned 7/5/2026 | tooltrust-scanner/v0.3.19

19 Low55 Info

Risk Summary

Safe With Normal Controls

Dep Visibility is the main signal, but overall risk remains within an acceptable range.

Potential impact: This finding indicates the tool should be reviewed before it is trusted.

Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.

Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.

Security Findings (74)

  • LowAS-011

    ℹ️Missing Rate-Limit / Timeout ×18

    tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration

    get-allowanceget-chain-by-idget-chain-by-nameget-chainsget-earn-chainsget-earn-portfolioget-earn-protocolsget-earn-vaultsget-gas-pricesget-native-token-balanceget-quote-with-callsget-routesget-step-transactionget-token-balanceget-token-balancesget-tokensget-toolstest-api-key

    Fix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.

  • LowAS-002

    ⚠️Excessive Permissions

    get-quote:input schema exposes 12 properties (threshold: 10)

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • InfoAS-002

    ⚠️Excessive Permissions ×18

    declared capabilities: code/command execution, network access

    get-allowanceget-gas-prices

    declared capabilities: network access

    get-chain-by-idget-chain-by-nameget-chainsget-earn-chainsget-earn-protocolsget-native-token-balanceget-token-balanceget-token-balancestest-api-key

    declared capabilities: HTTP requests

    get-earn-portfolioget-tools

    declared capabilities: filesystem access, HTTP requests

    get-earn-vaults

    declared capabilities: code/command execution

    get-quote-with-callsget-routesget-step-transactionget-tokens

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • InfoAS-010

    🔑Insecure Secret Handling ×12

    input parameter "tokenAddress" accepts a credential (informational; not evidence of insecure handling)

    get-allowanceget-token-balance

    input parameter "toToken" accepts a credential (informational; not evidence of insecure handling)

    get-connectionsget-quoteget-quote-with-calls

    input parameter "fromToken" accepts a credential (informational; not evidence of insecure handling)

    get-connectionsget-quoteget-quote-with-calls

    input parameter "toTokenAddress" accepts a credential (informational; not evidence of insecure handling)

    get-routes

    input parameter "fromTokenAddress" accepts a credential (informational; not evidence of insecure handling)

    get-routes

    input parameter "token" accepts a credential (informational; not evidence of insecure handling)

    get-token

    input parameter "tokenAddresses" accepts a credential (informational; not evidence of insecure handling)

    get-token-balances

    Fix: Avoid accepting raw credentials as input parameters. Use secret managers (e.g. 1Password CLI, AWS Secrets Manager) and ensure credentials are never logged or stored in agent traces.

  • InfoAS-014

    ℹ️Dependency Inventory Unavailable ×25

    Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.

    get-allowanceget-chain-by-idget-chain-by-nameget-chainsget-connectionsget-earn-chainsget-earn-portfolioget-earn-protocolsget-earn-vaultget-earn-vaultsget-gas-pricesget-gas-suggestionget-native-token-balanceget-quoteget-quote-with-callsget-routesget-statusget-step-transactionget-tokenget-token-balanceget-token-balancesget-tokensget-toolshealth-checktest-api-key

    Fix: Review and remediate the identified issue.

Scan this tool yourself

Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.

Install once, then scan any MCP server:

$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash
$ tooltrust-scanner scan --server "npx -y li-fi-lifi-mcp"

Adjust the package name if your npm registry name differs from the tool ID. View source

Add badge to your README

Copy this Markdown to show your ToolTrust grade on GitHub.

[![ToolTrust Grade A](https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-directory/main/docs/badges/grade-a.svg)](https://github.com/AgentSafe-AI/tooltrust-directory)