Home / MCP registry index / com.asyntai/support-agent
Asyntai
com.asyntai/support-agent in the official MCP registry.
Endpoint https://asyntai.com/mcp.
The registry describes it as: Run your website's AI support agent: knowledge, conversations, leads and live replies.
We read its 59 tools on 2026-10-26. Nothing in them matched our tool-poisoning rules. It also sets server instructions, text a client puts in front of the model on connect; those were read too.
A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.
Tools it advertises
list_websites get_account list_plans search_asyntai_docs get_asyntai_doc get_website create_website get_widget_settings update_widget_settings set_data_feed set_data_feed_max set_access_tags set_widget_pinning get_website_features update_website_features search_knowledge_base list_knowledge add_knowledge_text delete_knowledge_entry get_ai_instructions update_ai_instructions get_knowledge_entry add_knowledge_url set_knowledge_tags start_crawl list_crawls list_conversations get_conversation list_leads get_analytics list_visitor_questions list_knowledge_gaps list_images add_image delete_image list_products add_product delete_product list_booking_types list_embeds list_tickets list_webhooks add_webhook delete_webhook list_active_sessions take_over_conversation release_conversation send_agent_reply get_daily_report set_daily_report list_audit_log list_team_members list_widget_translations set_widget_translation list_proactive_messages save_proactive_message delete_proactive_message list_proactive_message_log ask_ai
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/com-asyntai-support-agent)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.