ToolTrust
B17/100
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: - 🏦 **Fiat escrows** — SPEI/wire deposits, KYC-gated release, dispute resolution - ⛓️ **Web3 escrows** — on-chain ERC-20 escrows with relayer, 7 supported chains - 🔐 **Confidential escrows** — FHE-encrypted amounts (Fhenix CoFHE) - 🔁 **Recurring payments** — subscription billing with auto-cycles - 🤖 **Agent trading** — wallet registration, P2P escrow between agents - 📦 **Delivery oracle** — auto-release on carrier delivery confirmation - 🔗 **Solana Blinks** — shareable payment links via Phantom Get your API key at [kustodia.app/register](https://kustodia.app/register)

By Smithery | 80 findings | Scanned 7/2/2026 | tooltrust-scanner/v0.3.19

1 High16 Low63 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 (80)

  • HighAS-003

    🔀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.

  • LowAS-002

    ⚠️Excessive Permissions ×2

    input schema exposes 19 properties (threshold: 10)

    create_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

    ℹ️Missing Rate-Limit / Timeout ×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-002

    ⚠️Excessive Permissions ×18

    declared capabilities: code/command execution, filesystem access

    create_escrowupload_evidence

    declared capabilities: code/command execution

    raise_disputefund_with_session_keypause_recurringresume_recurringcancel_recurringget_recurring_status

    declared capabilities: network access

    request_refundrelease_confidential_escrow

    declared capabilities: filesystem access

    create_web3_escrowcreate_session_keyget_trust_scorecreate_confidential_escrow

    declared capabilities: HTTP requests

    fund_agent_wallet

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

    create_solana_blink

    declared capabilities: network access, filesystem access

    get_escrow_evidence

    declared capabilities: filesystem access, HTTP requests

    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.

  • InfoAS-014

    ℹ️Dependency Inventory Unavailable ×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.

  • InfoAS-010

    🔑Insecure Secret Handling ×9

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

    create_web3_escrowfund_agent_walletcreate_confidential_escrowcreate_recurring_escrow

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

    fund_web3_escrow

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

    create_session_key

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

    fund_with_session_key

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

    register_agent_wallet

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

    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.

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