ToolTrust
A4/100
Smithery

syenite-ai-syenite

mcpsmithery

@Smithery

Composable DeFi intelligence for AI agents — lending rates and execution, yield, swap and bridge, prediction markets, position alerts with webhooks, wallet ops, and gas estimation across 30+ chains via MCP.

By Smithery | 112 findings | Scanned 7/4/2026 | tooltrust-scanner/v0.3.19

30 Low82 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 (112)

  • LowAS-011

    ℹ️Missing Rate-Limit / Timeout ×28

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

    syenite.helplending.rates.querylending.market.overviewlending.position.monitorlending.risk.assessyield.opportunitiesyield.assessswap.quoteswap.statusswap.multiwallet.balancestx.simulatetx.verifystrategy.carry.screenprediction.trendingprediction.searchprediction.bookfind.strategytx.receiptalerts.watchalerts.checkrates.watchprediction.watchprediction.orderkalshi.trendingkalshi.searchkalshi.bookprediction.arbitrage

    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 ×2

    input schema exposes 23 properties (threshold: 10)

    alerts.watch

    input schema exposes 14 properties (threshold: 10)

    rates.watch

    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 ×31

    declared capabilities: code/command execution

    syenite.helpyield.opportunitiesyield.assessswap.statusstrategy.carry.screenprediction.arbitrage

    declared capabilities: code/command execution, network access, HTTP requests

    lending.rates.query

    declared capabilities: code/command execution, network access, database access, HTTP requests

    lending.market.overview

    declared capabilities: code/command execution, HTTP requests

    lending.position.monitor

    declared capabilities: code/command execution, network access

    lending.risk.assessswap.multiprediction.booktx.receiptkalshi.book

    declared capabilities: code/command execution, network access, database access

    swap.quote

    declared capabilities: code/command execution, database access, HTTP requests

    wallet.balances

    declared capabilities: network access

    tx.simulateprediction.trendingkalshi.trending

    declared capabilities: network access, filesystem access

    tx.verify

    declared capabilities: network access, database access

    prediction.searchkalshi.search

    declared capabilities: code/command execution, filesystem access

    find.strategy

    declared capabilities: database access

    lending.supplyprediction.compare

    declared capabilities: code/command execution, network access, filesystem access, HTTP requests

    alerts.watch

    declared capabilities: HTTP requests

    alerts.check

    declared capabilities: network access, filesystem access, HTTP requests

    rates.watch

    declared capabilities: filesystem access

    alerts.remove

    declared capabilities: network access, HTTP requests

    prediction.watchprediction.order

    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-014

    ℹ️Dependency Inventory Unavailable ×46

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

    syenite.helplending.rates.querylending.market.overviewlending.position.monitorlending.risk.assessyield.opportunitiesyield.assessswap.quoteswap.statusswap.multiwallet.balancesgas.estimatetx.simulatetx.verifytx.guardstrategy.carry.screenprediction.trendingprediction.searchprediction.bookprediction.signalsfind.strategylending.supplylending.borrowlending.withdrawlending.repaytx.receipttoken.pricealerts.watchalerts.checkalerts.listrates.watchalerts.removemetamorpho.supplymetamorpho.withdrawprediction.marketprediction.watchprediction.positionprediction.quoteprediction.orderkalshi.trendingkalshi.searchkalshi.bookkalshi.marketkalshi.signalsprediction.compareprediction.arbitrage

    Fix: Review and remediate the identified issue.

  • InfoAS-010

    🔑Insecure Secret Handling ×5

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

    swap.quote

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

    swap.quote

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

    prediction.bookprediction.quoteprediction.order

    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.

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 syenite-ai-syenite"

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)