Loading…
Omnichannel messaging bridge enabling AI agents to send and receive messages via WhatsApp, email, and phone from a single unified API.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 1 month ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The kontato MCP server exposes 9 tools, focused primarily on communication capabilities. Its published description reads: "Omnichannel messaging bridge enabling AI agents to send and receive messages via WhatsApp, email, and phone from a single unified API". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates kontato F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Data-exfiltration parameters" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check kontato's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add kontato to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://api.kontato.ai/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
ATIVA a conta Kontato do telefone informado — cria apenas se ainda nao existir; se ja existe, reutiliza a MESMA conta (e normal e esperado chamar com conta existente: funciona como login). IDEMPOTENTE
Confirma o numero do dono com o codigo OTP de 6 digitos que chegou no WhatsApp dele apos o `provision`. OBRIGATORIO antes de enviar/agendar: ate verificar, `send`/`reply`/`schedule` retornam 403 owner
Registra uma entrega recorrente ou unica no scheduler do Kontato. No horario, o Kontato roda o `prompt` como um agente completo (com web/Exa) e entrega no WhatsApp do dono. USE ISTO para "todo dia me
Lista as entregas agendadas (recorrentes/unicas) desta conta, com proximo disparo.
Cancela uma entrega agendada pelo seu schedule_id (obtido em `list_schedules` ou `schedule`).
Envia uma mensagem de WhatsApp pelo numero-ponte do Kontato. CASO SEGURO: se OMITIR "to", entrega no WhatsApp do PROPRIO DONO (self-notification). REGRA TURN-BASED: voce nao executa trabalho no futuro
Responde a um numero especifico que mandou mensagem para o numero-ponte. Igual a `send`, mas "to" e OBRIGATORIO. Responder a quem te escreveu (reply-ratio alto) e mais seguro que cold outbound.
Lista o historico de mensagens do numero-ponte (recebidas e enviadas), mais recentes primeiro. Use para decidir a quem responder com `reply`.
Mostra o estado da conta Kontato: ativa ou nao, numero-ponte, e os schedules (rotinas) ja registrados. Use para honrar a regra turn-based: antes de dizer que algo sera entregue "todo dia", confirme aq
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: provision
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
ecisa lidar com api_key). Se a resposta vier com verification_required=RecommendationRemove side-channel parameters; constrain tool inputs.
tool: provision
A tool description tries to alter the model’s use of another tool.
eca OTP: chame `send` direto. Informe owner_phone (formato internaciRecommendationDescriptions must describe only their own tool.
tool: verify_number
A tool description tries to alter the model’s use of another tool.
pp dele apos o `provision`. OBRIGATORIO antes de enviar/agendar: ate veriRecommendationDescriptions must describe only their own tool.
tool: cancel_schedule
A tool description tries to alter the model’s use of another tool.
_schedules` ou `schedule`).RecommendationDescriptions must describe only their own tool.
tool: send
A tool description tries to alter the model’s use of another tool.
a registrar um schedule, nunca prometa entrega futura.RecommendationDescriptions must describe only their own tool.
tool: reply
A tool description tries to alter the model’s use of another tool.
ponte. Igual a `send`, mas "to" e OBRIGATORIO. Responder a quem te eRecommendationDescriptions must describe only their own tool.
tool: list_messages
A tool description tries to alter the model’s use of another tool.
responder com `reply`.RecommendationDescriptions must describe only their own tool.
tool: status
A tool description tries to alter the model’s use of another tool.
ui se existe um schedule ativo.RecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: provision
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: verify_number
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: schedule
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: list_schedules
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: cancel_schedule
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: send
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: reply
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: list_messages
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: status
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.