ToolTrust
C40/100
Smithery

kustodia-escrow

mcpsmithery

@Smithery

Agentic escrow payments for AI agents. Create, fund, and release escrow payments across fiat (MXN/USD via SPEI/wire) and crypto (USDC/USDT/MXNB on Arbitrum, Base, Polygon, Solana). **36 tools** covering: - ๐Ÿฆ **Fiat escrows** โ€” SPEI/wire deposits, KYC-gated release, dispute resolution - โ›“๏ธ **Web3 escrows** โ€” on-chain ERC-20 escrows with relayer, 7 supported chains - ๐Ÿ” **Confidential escrows** โ€” FHE-encrypted amounts (Fhenix CoFHE) - ๐Ÿ” **Recurring payments** โ€” subscription billing with auto-cycles - ๐Ÿค– **Agent trading** โ€” wallet registration, P2P escrow between agents - ๐Ÿ“ฆ **Delivery oracle** โ€” auto-release on carrier delivery confirmation - ๐Ÿ”— **Solana Blinks** โ€” shareable payment links via Phantom Get your API key at [kustodia.app/register](https://kustodia.app/register)

By Smithery | 86 findings | Scanned 6/3/2026 | tooltrust-scanner/v0.3.13

23 High9 Medium18 Low36 Info

Risk Summary

Needs Approval

Dep Visibility plus Excessive Permissions raises enough risk that this tool should not be auto-trusted.

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

Recommended action: Keep this tool behind manual approval and avoid unattended runs until the risky capabilities are narrowed or removed.

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

Security Findings (86)

  • HighAS-002

    โš ๏ธExcessive Permissions ร—13

    tool declares exec permission

    create_escrowupload_evidenceraise_disputefund_with_session_keycreate_solana_blinkpause_recurringresume_recurringcancel_recurringget_recurring_status

    tool declares network permission

    request_refundrelease_confidential_escrowcreate_solana_blinkget_escrow_evidence

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

  • HighAS-010

    ๐Ÿ”‘Insecure Secret Handling ร—9

    input parameter "token" appears to accept a secret or credential

    create_web3_escrowfund_agent_walletcreate_confidential_escrowcreate_recurring_escrow

    input parameter "agent_private_key" appears to accept a secret or credential

    fund_web3_escrow

    input parameter "token_address" appears to accept a secret or credential

    create_session_key

    input parameter "token_decimals" appears to accept a secret or credential

    fund_with_session_key

    input parameter "supported_tokens" appears to accept a secret or credential

    register_agent_wallet

    input parameter "tokens" appears to accept a secret or credential

    check_balance

    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.

  • HighAS-003

    ๐Ÿ”€Scope Mismatch

    get_recurring_status:tool name "get_recurring_status" implies read-only operation but declares exec permission

    Fix: Ensure tool names, descriptions, and permission declarations are internally consistent. Use explicit naming conventions that fully reflect actual capabilities.

  • MediumAS-002

    โš ๏ธExcessive Permissions ร—9

    tool declares fs permission

    create_escrowupload_evidencecreate_web3_escrowcreate_session_keyget_trust_scorecreate_confidential_escrowcreate_solana_blinkget_escrow_evidencecreate_recurring_escrow

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

  • LowAS-002

    โš ๏ธExcessive Permissions ร—4

    input schema exposes 19 properties (threshold: 10)

    create_escrow

    tool declares http permission

    fund_agent_walletcreate_recurring_escrow

    input schema exposes 13 properties (threshold: 10)

    create_recurring_escrow

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

  • LowAS-011

    โ„น๏ธMissing Rate-Limit / Timeout ร—14

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

    create_escrowupload_evidenceraise_disputerequest_refundfund_with_session_keyfund_agent_walletrelease_confidential_escrowcreate_solana_blinkget_escrow_evidencecreate_recurring_escrowpause_recurringresume_recurringcancel_recurringget_recurring_status

    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.

  • InfoAS-014

    โ„น๏ธDependency Inventory Unavailable ร—36

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

    create_escrowcheck_statusrelease_fundsupload_evidenceget_fx_ratelist_paymentscancel_paymentraise_disputerequest_refundcreate_web3_escrowfund_web3_escrowrelease_web3_escrowdispute_web3_escrowcheck_web3_statuslist_web3_escrowsget_web3_escrowcreate_session_keyfund_with_session_keyregister_agent_walletfund_agent_walletlist_trade_offersaccept_tradecheck_balanceget_trust_scorecreate_confidential_escrowfund_confidential_escrowrelease_confidential_escrowcreate_solana_blinkget_escrow_evidencecreate_recurring_escrowpause_recurringresume_recurringcancel_recurringapprove_cyclelist_recurringget_recurring_status

    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 kustodia-escrow"

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 C](https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-directory/main/docs/badges/grade-c.svg)](https://github.com/AgentSafe-AI/tooltrust-directory)