# Asyntai (remote · asyntai.com)

Run your website's AI support agent: knowledge, conversations, leads and live replies.

- Trust score: 83/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- remote · `asyntai.com`: 83/100 (this document), [markdown](https://verifymcp.io/servers/com-asyntai-support-agent/asyntai.md), [page](https://verifymcp.io/servers/com-asyntai-support-agent/asyntai)
- npm · `@asyntai/mcp`: 44/100, [markdown](https://verifymcp.io/servers/com-asyntai-support-agent/asyntai-mcp.md), [page](https://verifymcp.io/servers/com-asyntai-support-agent/asyntai-mcp)

## Channel facts

- Endpoint: `https://asyntai.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-21.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 85/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 4639 tokens (~85/item across 54 items; 54 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 43/100
  - Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 5 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 55 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the Asyntai MCP server?

Asyntai is a hosted endpoint at https://asyntai.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-asyntai-support-agent 'https://asyntai.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-asyntai-support-agent": {
      "url": "https://asyntai.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-asyntai-support-agent": {
      "type": "http",
      "url": "https://asyntai.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-asyntai-support-agent]
url = "https://asyntai.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-asyntai-support-agent": {
      "type": "remote",
      "url": "https://asyntai.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-asyntai-support-agent --url 'https://asyntai.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-asyntai-support-agent:
    url: "https://asyntai.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-asyntai-support-agent": {
      "Transport": "http",
      "Url": "https://asyntai.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-asyntai-support-agent -t streamable-http -u 'https://asyntai.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-asyntai-support-agent": {
      "type": "http",
      "url": "https://asyntai.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-20 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-11 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-09 (score 78, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-09-08 (score 77, +41)

- [security improvement] Transport: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Authorization: Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Destructive annotations: 100

### 2026-09-02 (score 36)

First indexed and scored.

## MCP tools (54)

### `list_websites` (~42 tokens)

List websites

List the websites (AI agents) on this Asyntai account, with the id every other tool takes. Start here when the account may have more than one.

### `get_account` (~31 tokens)

Get account and usage

Get the signed-in account's email, plan, and how many chat messages it has used against its monthly allowance.

### `list_plans` (~50 tokens)

Compare plans

List every Asyntai plan with its price, monthly message allowance and the features it includes, alongside the plan this account is on. Use it to answer which plan someone should move to, and why.

### `search_asyntai_docs` (~146 tokens)

Search the Asyntai documentation

Search Asyntai's own product documentation and get back the pages that match, with a short excerpt from each. Use this to find out how a feature works before changing anything, rather than guessing. This searches Asyntai's documentation, NOT the customer's own content: for that, use search_knowledge_base. Matching is by keyword, so if the results look wrong, search again using Asyntai's own feature names, for example data feed, widget pinning, access tags, AI instructions.

Input parameters:

- `limit` (integer): How many pages to return, 1 to 20. Default 8.
- `query` (string, required): What to look for.

### `get_asyntai_doc` (~65 tokens)

Read one documentation page

Read one page of Asyntai's documentation in full, given the url or slug from search_asyntai_docs, for example /documentation/mcp/ or just mcp.

Input parameters:

- `page` (string, required): The url or slug of the page to read.

### `get_website` (~64 tokens)

Get one website

Get the full record for one website: its name, domain, platform, widget id and the embed code to paste into the site.

Input parameters:

- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `create_website` (~109 tokens)

Add a website

Add a new website (a new AI agent) to the account and return its embed code. Each plan allows a limited number of websites, and this refuses once that limit is reached. By default it also starts a crawl of the site to build the knowledge base.

Input parameters:

- `crawl` (boolean): Crawl the site after adding it. True by default.
- `domain` (string, required): The website address, for example shop.example.com.
- `name` (string): Display name for this agent. Optional.

### `get_widget_settings` (~86 tokens)

Get the chat widget settings

Read all appearance and behaviour settings for one website's chat widget: colours, greeting, position, auto-trigger, data collection, bookings and the rest. Also returns which settings this account's plan cannot change, and the plan each of those needs.

Input parameters:

- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `update_widget_settings` (~120 tokens)

Change the chat widget settings

Change one or more chat widget settings. Pass an object of setting name to new value; read them with get_widget_settings first. Changes are live for every visitor at once. Settings the plan does not include are refused with the plan they need, and nothing is written unless every value is valid.

Input parameters:

- `settings` (object, required): Setting name to new value, for example widget_color set to #6366f1.
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `set_data_feed` (~122 tokens)

Set the Real-Time Data Feed

Point the chatbot at a product feed and index it. This fetches the feed, checks it really is a feed, clears whatever was indexed before, and rebuilds the index in the background. Send an empty url to remove the feed. Needs the Standard plan or higher.

Input parameters:

- `enabled` (boolean): Whether the chatbot may use the feed.
- `url` (string, required): Address of the product feed. Empty removes it.
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `set_data_feed_max` (~109 tokens)

Set the Real-Time Data Feed Max

Same as set_data_feed, for the Max tier, which indexes a larger catalogue. Fetches, validates, clears the old index and rebuilds it in the background. Needs the Pro plan or higher.

Input parameters:

- `enabled` (boolean): Whether the chatbot may use the feed.
- `url` (string, required): Address of the product feed. Empty removes it.
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `set_access_tags` (~80 tokens)

Turn Access Tags on or off

Switch Access Tags on or off for one website. Turning it on creates the signing secret your server needs to sign visitor entitlements. Needs the Enterprise plan.

Input parameters:

- `enabled` (boolean, required): True to switch it on.
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `set_widget_pinning` (~89 tokens)

Turn Widget Pinning on or off

Freeze the chat widget at its current version, so the site always serves the same copy with an integrity hash. Turning it on builds that snapshot and changes the embed code. Needs the Enterprise plan.

Input parameters:

- `enabled` (boolean, required): True to pin the widget.
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `get_website_features` (~115 tokens)

Get the website features

Read the plan-gated features for one website: Real-Time Data Feed and its Max tier, Product Cards, Dynamic Images, User Context, Link Parameters, Chat Retention, Chat Categories, Access Tags, Widget Pinning, Zero Retention, PII Redaction and the Output Classifier. Shows current values, which features the plan allows, and the plan each locked feature needs.

Input parameters:

- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `update_website_features` (~131 tokens)

Change the website features

Turn website features on or off and set their values, for example the Real-Time Data Feed URL or the PII Redaction rules. Pass an object of field name to value; read them with get_website_features first. A feature the plan does not include is refused with the plan it needs. These change how the live chatbot behaves for every visitor.

Input parameters:

- `fields` (object, required): Field name to new value, for example real_time_products_enabled set to true.
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `search_knowledge_base` (~122 tokens)

Search the knowledge base

Search one website's knowledge base and return the passages the chatbot would retrieve for this question, with a relevance score. Use this to check what the chatbot knows about a topic. It does not generate an answer and does not use the message allowance.

Input parameters:

- `limit` (integer): How many passages to return (1-20, default 5).
- `query` (string, required): What to look for, in plain language.
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `list_knowledge` (~78 tokens)

List knowledge base entries

List the sources in one website's knowledge base: uploaded text, documents, added pages and crawls.

Input parameters:

- `limit` (integer): How many entries to return (1-100, default 50).
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `add_knowledge_text` (~109 tokens)

Add text to the knowledge base

Add a titled block of text to one website's knowledge base. The chatbot can use it in answers as soon as this returns. Adds a new entry; it never replaces an existing one.

Input parameters:

- `content` (string, required): The text itself. At least 10 characters.
- `title` (string, required): Short name for this entry, shown in the dashboard.
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `delete_knowledge_entry` (~52 tokens)

Delete a knowledge base entry

Permanently delete one knowledge base entry and every passage built from it. The chatbot stops using that content immediately. This cannot be undone.

Input parameters:

- `entry_id` (string, required): The entry id from list_knowledge.

### `get_ai_instructions` (~57 tokens)

Get the AI instructions

Get the instructions that shape how one website's chatbot answers: its role, tone and rules.

Input parameters:

- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `update_ai_instructions` (~96 tokens)

Replace the AI instructions

Replace one website's AI instructions with new text. This overwrites the current instructions and changes how the live chatbot answers every visitor. Read them with get_ai_instructions first, and show the user what will change before calling this.

Input parameters:

- `instructions` (string, required): The full new instructions text.
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `get_knowledge_entry` (~71 tokens)

Read one knowledge base entry

Read the stored text of one knowledge base entry. Works for the content you supplied: text, documents, spreadsheets, single pages and videos. A website crawl is listed but not exported, because the source is your own public site.

Input parameters:

- `entry_id` (string, required): The entry id from list_knowledge.

### `add_knowledge_url` (~87 tokens)

Add a page to the knowledge base

Fetch one web page and add its text to the knowledge base. Use this for a single page. To take in a whole site, use start_crawl instead.

Input parameters:

- `url` (string, required): Full address of the page, including https://.
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `set_knowledge_tags` (~92 tokens)

Set Access Tags on an entry

Restrict who can retrieve one knowledge base entry. A visitor must present a matching tag, signed by your own server, before the chatbot will use the entry. Send an empty list to make it public again. Access Tags needs the Enterprise plan.

Input parameters:

- `access_tags` (array, required): Tag names. An empty list makes the entry public.
- `entry_id` (string, required): The entry id from list_knowledge.

### `start_crawl` (~121 tokens)

Crawl a website into the knowledge base

Crawl a website and add its pages to the knowledge base. Runs in the background; check on it with list_crawls. Each plan caps the pages per crawl, and asking for more than the cap is refused.

Input parameters:

- `max_pages` (integer): How many pages to take at most. Capped by the plan.
- `start_url` (string): Where to start. Defaults to the website's own domain.
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `list_crawls` (~81 tokens)

List crawl jobs

List recent crawl jobs for one website with their status, how many pages they took, and why each one stopped.

Input parameters:

- `limit` (integer): How many jobs to return (1-50, default 10).
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `list_conversations` (~126 tokens)

List recent conversations

List recent visitor conversations for one website, newest first, with the session id, message count and any email or phone the visitor gave.

Input parameters:

- `days` (integer): How many days back to look (1-90, default 7).
- `limit` (integer): How many conversations to return (1-100, default 20).
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.
- `with_leads_only` (boolean): Only return conversations where the visitor left an email or phone.

### `get_conversation` (~60 tokens)

Read one conversation

Read the full message history of one conversation, in order, from its session id.

Input parameters:

- `limit` (integer): How many messages to return (1-200, default 100).
- `session_id` (string, required): Session id from list_conversations.

### `list_leads` (~79 tokens)

List captured leads

List the email addresses and phone numbers visitors left in chat, newest first, with the page they were on.

Input parameters:

- `limit` (integer): How many leads to return (1-100, default 50).
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `get_analytics` (~87 tokens)

Get chat analytics

Summarise one website's chat activity over a period: conversations, messages, leads captured, escalations, and the countries visitors came from.

Input parameters:

- `days` (integer): How many days back to measure (1-90, default 30).
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `list_knowledge_gaps` (~139 tokens)

List knowledge gaps

List the Knowledge Gaps Asyntai recorded: real visitor questions the chatbot could not answer. Use this to find what to fill in with add_knowledge_text. Needs the Standard plan or higher.

Input parameters:

- `days` (integer): How many days back to look (1-90, default 30).
- `include_resolved` (boolean): Include gaps already marked as resolved. Off by default.
- `limit` (integer): How many gaps to return (1-100, default 25).
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `list_images` (~58 tokens)

List the images the chatbot can show

List the images the chatbot may show a visitor, with the description that tells it when each one is relevant.

Input parameters:

- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `add_image` (~100 tokens)

Add an image the chatbot can show

Add an image the chatbot may show. The description is what the AI reads to decide when the image answers the question, so describe what it shows and when it helps.

Input parameters:

- `description` (string, required): What the image shows and when the chatbot should send it.
- `image_url` (string, required): Address of the image.
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `delete_image` (~31 tokens)

Delete an image

Remove one image so the chatbot stops showing it.

Input parameters:

- `image_id` (integer, required): Image id from list_images.

### `list_products` (~60 tokens)

List the product cards

List the products the chatbot can show as cards, with price and links. Product Cards needs the Standard plan or higher.

Input parameters:

- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `add_product` (~118 tokens)

Add a product card

Add a product the chatbot can show as a card. Needs the Standard plan or higher.

Input parameters:

- `description` (string): Short description shown on the card.
- `image_url` (string): Address of the product image.
- `name` (string, required): Product name.
- `price` (string): Price as text, for example 29 EUR.
- `product_link` (string): Address of the product page.
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `delete_product` (~31 tokens)

Delete a product card

Remove one product so the chatbot stops offering it.

Input parameters:

- `product_id` (integer, required): Product id from list_products.

### `list_booking_types` (~65 tokens)

List the booking types

List the appointment types visitors can book, with length, price and how many spots each has. Bookings needs the Standard plan or higher.

Input parameters:

- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `list_embeds` (~65 tokens)

List the embeds

List the third-party tools embedded in the chat, such as a booking calendar or a form. Embeds needs the Standard plan or higher.

Input parameters:

- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `list_tickets` (~99 tokens)

List support tickets

List support tickets raised from chat, with status, priority and the visitor's details. Needs the Standard plan or higher.

Input parameters:

- `limit` (integer): How many tickets to return (1-100, default 25).
- `status` (string): Only tickets with this status, for example open or resolved.
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `list_webhooks` (~36 tokens)

List webhooks

List the webhooks registered on this account. The signing secret is never returned; it is shown once, when the webhook is created.

### `add_webhook` (~97 tokens)

Add a webhook

Register a URL to receive events, for example every new message. Returns a signing secret once; store it, because it is never shown again. Needs a paid plan.

Input parameters:

- `events` (array, required): Event names to subscribe to.
- `url` (string, required): HTTPS address that will receive the events.
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `delete_webhook` (~36 tokens)

Delete a webhook

Delete one webhook. Events stop reaching that address at once.

Input parameters:

- `webhook_id` (string, required): The webhook id from list_webhooks.

### `list_active_sessions` (~98 tokens)

List visitors chatting right now

List the visitors currently in a chat: which page they are on, their country, how long they have been there, and whether a human has taken the conversation over. Needs the Standard plan or higher.

Input parameters:

- `limit` (integer): How many sessions to return (1-100, default 25).
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `take_over_conversation` (~66 tokens)

Take a conversation over from the AI

Stop the AI answering one conversation so a human can reply instead. The visitor is told a person has joined. Use send_agent_reply afterwards, and release_conversation when done. Needs the Standard plan or higher.

Input parameters:

- `session_id` (string, required): Session id from list_active_sessions.

### `release_conversation` (~42 tokens)

Give a conversation back to the AI

Hand a taken-over conversation back to the AI, which answers the visitor again from the next message.

Input parameters:

- `session_id` (string, required): Session id of the conversation.

### `send_agent_reply` (~103 tokens)

Send a message to a visitor

Send a message, as a human agent, to a real visitor who is chatting right now. Take the conversation over first. The visitor sees this immediately, so show the user the exact wording and get their agreement before calling this.

Input parameters:

- `agent_name` (string): Name shown to the visitor. Defaults to the account's agent name.
- `message` (string, required): The text to send to the visitor.
- `session_id` (string, required): Session id of the conversation.

### `get_daily_report` (~57 tokens)

Get the daily report setting

Say whether the daily email summary is on for one website, and when the last one went out.

Input parameters:

- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `set_daily_report` (~70 tokens)

Turn the daily report on or off

Turn the daily email summary of chats on or off for one website. Needs the Standard plan or higher.

Input parameters:

- `enabled` (boolean, required): True to switch it on.
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `list_audit_log` (~92 tokens)

Read the audit log

Read the record of what changed on this account: who did it, when, and from where. Recorded on the Enterprise plan only.

Input parameters:

- `category` (string): Only entries in this category. Optional.
- `days` (integer): How many days back to read (1-90, default 30).
- `limit` (integer): How many entries to return (1-100, default 50).

### `list_team_members` (~30 tokens)

List team members

List the people who share this account, what each may reach, and how many seats the plan allows.

### `list_widget_translations` (~60 tokens)

List the widget translations

List the languages the chat widget has its own wording for, with the greeting and agent name used in each.

Input parameters:

- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `set_widget_translation` (~126 tokens)

Set the widget wording for one language

Set the chat widget's greeting, agent name and bubble text for one language. A visitor in that language sees this wording instead of the default.

Input parameters:

- `ai_support_name` (string): Agent name shown in the header.
- `initial_message` (string): The greeting the visitor sees first.
- `language_code` (string, required): Language code, for example de or fr.
- `notification_bubble_text` (string): Text of the notification bubble.
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

### `ask_ai` (~125 tokens)

Ask the chatbot a question

Ask one website's chatbot a question and get the answer a real visitor would receive. Use this to test the bot. It spends one message from the account's monthly allowance, and it calls an external model provider.

Input parameters:

- `message` (string, required): The question to ask, as a visitor would type it.
- `session_id` (string): Reuse the same value across calls to continue one test conversation. Omit to start a fresh one.
- `website_id` (integer): Numeric id of the website, from list_websites. Omit to use the account's primary website.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-asyntai-support-agent/asyntai#diagnostics

## Score history

- 2026-09-21: 83
- 2026-09-20: 83
- 2026-09-19: 82
- 2026-09-18: 82
- 2026-09-17: 82
- 2026-09-16: 81
- 2026-09-15: 81
- 2026-09-14: 80
- 2026-09-13: 80
- 2026-09-12: 79
- 2026-09-11: 79
- 2026-09-10: 78
- 2026-09-09: 78
- 2026-09-08: 77
- 2026-09-07: 36
- 2026-09-06: 36
- 2026-09-05: 36
- 2026-09-04: 36
- 2026-09-03: 36
- 2026-09-02: 36

## Common questions

### What is the Asyntai MCP server?

Asyntai is an MCP server listed in the public MCP registry as com.asyntai/support-agent. Run your website's AI support agent: knowledge, conversations, leads and live replies. This page covers its hosted endpoint (https://asyntai.com/mcp).

### Is the Asyntai MCP server safe to use?

Asyntai scores 83 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Asyntai MCP server expose?

Asyntai exposes 54 tools: list_websites, get_account, list_plans, search_asyntai_docs, get_asyntai_doc, and 49 more. Their descriptions and schemas cost roughly 4,481 tokens of context every time the server is loaded.

### Does the Asyntai MCP server require authentication?

Yes. Asyntai asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Asyntai MCP server still maintained?

Asyntai is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://asyntai.com/mcp
- Website: https://asyntai.com/documentation/mcp/
- Changelog RSS feed: https://verifymcp.io/servers/com-asyntai-support-agent/asyntai.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-asyntai-support-agent/asyntai.json
- HTML version of this page: https://verifymcp.io/servers/com-asyntai-support-agent/asyntai