# HeyCAi Clinic Tools (remote · www.heycai.ai)

Front-desk revenue loss calculator and website AI-search check for health clinics, by HeyCAi

- Trust score: 73/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `www.heycai.ai`: 73/100 (this document), [markdown](https://verifymcp.io/servers/ai-heycai-clinic-tools/www.md), [page](https://verifymcp.io/servers/ai-heycai-clinic-tools/www)

## Channel facts

- Endpoint: `https://www.heycai.ai/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 2026-11-21.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 57/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1601 tokens (~533/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 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.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the HeyCAi Clinic Tools MCP server?

HeyCAi Clinic Tools is a hosted endpoint at https://www.heycai.ai/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 ai-heycai-clinic-tools 'https://www.heycai.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-heycai-clinic-tools": {
      "url": "https://www.heycai.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-heycai-clinic-tools": {
      "type": "http",
      "url": "https://www.heycai.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-heycai-clinic-tools]
url = "https://www.heycai.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-heycai-clinic-tools": {
      "type": "remote",
      "url": "https://www.heycai.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-heycai-clinic-tools --url 'https://www.heycai.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-heycai-clinic-tools:
    url: "https://www.heycai.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-heycai-clinic-tools": {
      "Transport": "http",
      "Url": "https://www.heycai.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-heycai-clinic-tools -t streamable-http -u 'https://www.heycai.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-heycai-clinic-tools": {
      "type": "http",
      "url": "https://www.heycai.ai/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.

### 2026-11-19 (score 73, +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.

### 2026-11-17 (score 72, +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.

### 2026-11-15 (score 71, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-14 (score 70)

First indexed and scored.

## MCP tools (3)

### `estimate_front_desk_loss` (~1169 tokens)

Estimate front-desk revenue loss

Estimates how much revenue a health clinic loses each month to unanswered phone calls, WhatsApp conversations that wait for a reply, and no-shows, from figures the clinic provides (a single value or a low–high range for each). A leak without its figures comes back as pending with the figures it needs; nothing is filled with averages or benchmarks. Returns monthly and yearly amounts per leak with the arithmetic, a check against the clinic's free appointment slots, and categories of fixes. Counts and percentages only: never send patient names or records.

Input parameters:

- `afterHoursMissedPercent`: Uout: Optional: of the unanswered calls, the share made outside opening hours (% of unanswered calls). A number, or {"low", "high"} for a range. 0–100: 30 means 30%.
- `appointmentsPerMonth`: A: Appointments booked (appointments per month). A number, or {"low", "high"} for a range.
- `appointmentsPerWeek`: A: Appointments booked (appointments per week). A number, or {"low", "high"} for a range.
- `callDaysPerMonth`: D: Days a month the calls in `C` come in (days per month). A number, or {"low", "high"} for a range.
- `currency` (string): ISO 4217 code of the clinic's currency, such as EUR, GBP or USD: money in the result then carries its symbol.
- `feePerVisit`: F: Average fee per visit (the clinic's currency). A number, or {"low", "high"} for a range.
- `freeSlotsPerMonth`: K: Free appointment slots: appointments the clinic could still book in a month with its current team and hours (appointments per month). A number, or {"low", "high"} for a range.
- `inboundCallsPerDay`: C: Inbound calls (calls per day). A number, or {"low", "high"} for a range.
- `inboundCallsPerMonth`: C×D: Inbound calls (calls per month). A number, or {"low", "high"} for a range.
- `newPatientCallsPercent`: N: Calls that come from new patients (% of inbound calls). A number, or {"low", "high"} for a range. 0–100: 30 means 30%.
- `newPatientValue`: V: Revenue from one new patient (the clinic's currency). A number, or {"low", "high"} for a range.
- `newPatientsLostPercent`: L: New patients not reached who never call back or book (% of new patients not reached). A number, or {"low", "high"} for a range. 0–100: 30 means 30%.
- `noShowPercent`: R: No-shows: the patient does not come and gives no notice (% of booked appointments). A number, or {"low", "high"} for a range. 0–100: 30 means 30%.
- `refilledNoShowPercent`: S: Of the no-show slots, the share filled again by another patient (% of no-shows). A number, or {"low", "high"} for a range. 0–100: 30 means 30%.
- `repeatAttemptsPercent`: X: If `Mu` is not available: of the unanswered calls, the share that are repeat attempts by a caller already counted (% of unanswered calls). A number, or {"low", "high"} for a range. 0–100: 30 means…
- `unansweredCallsPercent`: U: Calls not answered (missed, abandoned or sent to voicemail) (% of inbound calls). A number, or {"low", "high"} for a range. 0–100: 30 means 30%.
- `uniqueMissedCallersPerMonth`: Mu: Best, if the report gives it: unique numbers among the unanswered calls, each caller counted once however many times they called (numbers per month). A number, or {"low", "high"} for a range.
- `visitsPerNewPatient`: T: Visits per new patient, on average (visits). A number, or {"low", "high"} for a range.
- `whatsappConversationsPerDay`: W: WhatsApp conversations started by patients (count people, not individual messages) (conversations per day). A number, or {"low", "high"} for a range.
- `whatsappConversationsPerMonth`: W×Dw: WhatsApp conversations started by patients (count people, not individual messages) (conversations per month). A number, or {"low", "high"} for a range.
- `whatsappDaysPerMonth`: Dw: Days a month messages come in (messages can arrive on closed days too: ask) (days per month). A number, or {"low", "high"} for a range.
- `whatsappNewPatientPercent`: Nw: Conversations from new patients (% of conversations). A number, or {"low", "high"} for a range. 0–100: 30 means 30%.
- `whatsappNewPatientsLostPercent`: Lw: Of the new patients who waited, the share who never booked (% of those who waited). A number, or {"low", "high"} for a range. 0–100: 30 means 30%.
- `whatsappWaitingPercent`: O: Conversations that wait for a reply: sent outside opening hours, or left unanswered (% of conversations). A number, or {"low", "high"} for a range. 0–100: 30 means 30%.

Output parameters:

- `callsSplit`
- `capacity` (object)
- `currency` (string|null)
- `derived` (array)
- `figures` (array)
- `footer` (string)
- `leaks` (array): The largest calculated leak first, pending leaks last.
- `options` (array)
- `questions` (array): One question per figure still needed, with its unit and where the clinic finds it.
- `questionsForSuppliers` (array)
- `repeatAdjustment` (string)
- `revenueNote` (string)
- `total`: The calculated leaks added up; null when none is calculated.

### `check_clinic_website_ai_readiness` (~209 tokens)

Check a clinic website's AI-search readiness

Checks a health clinic's public website for what lets Google and AI search engines read and cite it. Fetches only the home page, /robots.txt, /llms.txt and /sitemap.xml of the address given, and returns structured findings: which AI crawlers robots.txt lets read the home page (GPTBot, OAI-SearchBot, ClaudeBot, Claude-SearchBot, PerplexityBot, Google-Extended, Bingbot), llms.txt and sitemap presence, HTTPS, title and meta description, noindex, clinic schema.org JSON-LD (type, name, address, telephone, opening hours), hreflang, and one-tap call, WhatsApp and booking links, with a prioritised list of fixes. Reads public pages only and returns no page text beyond the title and meta description.

Input parameters:

- `url` (string, required): The clinic website, for example https://www.example-clinic.com (http or https; a bare domain works).

Output parameters:

- `findings` (array): High first, then medium, then low.
- `footer` (string)
- `home` (object): The home page as served, without running JavaScript.
- `https` (boolean): Whether the home page ended on an https URL (the address checked, when the home page did not answer).
- `llmsTxt` (object)
- `pagesRead` (array): The home page, robots.txt, llms.txt and sitemap.xml, in that order.
- `robotsTxt` (object)
- `site` (string): The origin checked (scheme and host); a deep address checks the home page of its site.
- `sitemapXml` (object)

### `about_heycai` (~103 tokens)

About HeyCAi

Facts about HeyCAi, the publisher of these tools, from its own website: what its AI receptionist does for clinics, the practice software it books into, its languages, how it introduces itself to patients, and links to its pricing calculator, demo and contact pages. Use it only when the user asks about HeyCAi. lang: en (default) or es.

Input parameters:

- `lang` (string): Language of the answer: en (default) or es.

Output parameters:

- `company` (object)
- `facts` (array): Verified facts, word for word from the website.
- `lang` (string)
- `links` (object)
- `summary` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-heycai-clinic-tools/www#diagnostics

## Score history

- 2026-11-21: 73
- 2026-11-20: 73
- 2026-11-19: 73
- 2026-11-18: 72
- 2026-11-17: 72
- 2026-11-16: 71
- 2026-11-15: 71
- 2026-11-14: 70

## Common questions

### What is the HeyCAi Clinic Tools MCP server?

HeyCAi Clinic Tools is an MCP server listed in the public MCP registry as ai.heycai/clinic-tools. Front-desk revenue loss calculator and website AI-search check for health clinics, by HeyCAi. This page covers its hosted endpoint (https://www.heycai.ai/mcp).

### Is the HeyCAi Clinic Tools MCP server safe to use?

HeyCAi Clinic Tools scores 73 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 HeyCAi Clinic Tools MCP server expose?

HeyCAi Clinic Tools exposes 3 tools: estimate_front_desk_loss, check_clinic_website_ai_readiness, about_heycai. Their descriptions and schemas cost roughly 1,481 tokens of context every time the server is loaded.

### Does the HeyCAi Clinic Tools MCP server require authentication?

No. We connected to HeyCAi Clinic Tools without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the HeyCAi Clinic Tools MCP server still maintained?

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

### What did VerifyMCP test on the HeyCAi Clinic Tools MCP server?

VerifyMCP ran 13 checks on HeyCAi Clinic Tools, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://www.heycai.ai/mcp
- Website: https://www.heycai.ai/mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/ai-heycai-clinic-tools/www.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-heycai-clinic-tools/www/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ai-heycai-clinic-tools/www.json
- HTML version of this page: https://verifymcp.io/servers/ai-heycai-clinic-tools/www
