mcpwatch

← All servers

Grade B

Kivel

io.kivel/kivel · v0.4.0 · score 89/100 · checked 2026-11-22

Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works

Email inboxes, webhook URLs, mock APIs and 170+ tools for coding agents over one MCP connection.

Source: https://github.com/TangoBeee/kivel

Findings

SeverityRuleDetail
LowMW005Remote endpoint lists 67 tool(s) to anyone, no credentials needed.
MediumMW1026 tool(s) can execute commands or delete data (delete_authenticator, delete_webhook_inbox, delete_monitor, memory_delete, delete_mock_api and 1 more). Require confirmation before the agent calls them.

What was checked

Public tools: create_test_wallet, wallet_balance, wallet_pay, list_wallet_transactions, create_test_paywall, create_test_checkout, complete_test_checkout, save_credential, list_credentials, reveal_credential, generate_password, add_authenticator, get_totp_code, list_authenticators, delete_authenticator, get_email_attachment, create_oauth_provider, create_phone_number, list_phone_numbers, release_phone_number, list_sms, wait_for_sms, call_mock_api, create_webhook_inbox, inspect_webhook_inbox, wait_for_webhook, set_webhook_response, delete_webhook_inbox, create_email_inbox, wait_for_email

Maintainer? Add the badge

Grades refresh daily. Think a finding is wrong? Dispute this grade.

[![mcpwatch](https://www.mcpwatch.io/badge/io-kivel-kivel-adde7d38.svg)](https://www.mcpwatch.io/s/io-kivel-kivel-adde7d38)