# io.github.pinalmdave/bookrails (remote · bookrails-api.azurewebsites.net)

Find, compare, and book local service businesses: live availability, prices, reviews, booking.

- Trust score: 59/100 (low)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `bookrails-api.azurewebsites.net`: 59/100 (this document), [markdown](https://verifymcp.io/servers/pinalmdave-bookrails/bookrails-api.md), [page](https://verifymcp.io/servers/pinalmdave-bookrails/bookrails-api)

## Channel facts

- Endpoint: `https://bookrails-api.azurewebsites.net/mcp/`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.0.0`

## 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 2026-08-03.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (cancel_or_reschedule).
  - HTTPS not yet verified: we couldn't determine whether a plaintext access path exists.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 66/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1764 tokens (~135/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 82/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 37% of tool parameters carry a description.
  - Structured output schemas are declared (31% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http pinalmdave-bookrails https://bookrails-api.azurewebsites.net/mcp/
```

### Codex

```toml
[mcp_servers.pinalmdave-bookrails]
url = "https://bookrails-api.azurewebsites.net/mcp/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "pinalmdave-bookrails": {
      "type": "remote",
      "url": "https://bookrails-api.azurewebsites.net/mcp/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add pinalmdave-bookrails --url https://bookrails-api.azurewebsites.net/mcp/ --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  pinalmdave-bookrails:
    url: "https://bookrails-api.azurewebsites.net/mcp/"
```

### Other

```json
{
  "mcpServers": {
    "pinalmdave-bookrails": {
      "type": "http",
      "url": "https://bookrails-api.azurewebsites.net/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.

### 2026-08-03 (score 59, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 58, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 57, −1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 58, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 57, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 56, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 55)

First indexed and scored.

## MCP tools (13)

### `search_businesses` (~184 tokens)

Find top-rated local service businesses matching a need near a location.

    Returns ranked businesses with rating, distance, price band, one-line
    highlight, the soonest available slot, and a hosted booking URL. Results
    are bookable directly via check_availability + book_appointment.

Input parameters:

- `category`: Filter by vertical
- `location` (string, required): City/neighborhood/ZIP, e.g. 'Edison, NJ' or '08817'
- `max_results` (integer)
- `min_rating`
- `open_now` (boolean): Only businesses open right now
- `query` (string, required): Natural-language need, e.g. 'gel manicure', 'emergency water heater repair', 'deep tissue massage'. Not a business name — use get_business_details if the user names a business.
- `radius_km` (number)

Output parameters:

- `result` (array)

### `get_business_details` (~100 tokens)

Get a business's full profile: services with prices and durations,
    hours, booking and cancellation policies, review summary, photos, and
    hosted booking page URL. Call this before quoting prices to the user.

    Returns: {business: BusinessSummary, services: list[ServiceItem],
    hours: dict[str, str], policy: BookingPolicy, review_summary: str}

Input parameters:

- `business_id` (string, required): ID from search_businesses

### `check_availability` (~134 tokens)

List open, bookable time slots for one service from the business's
    live calendar. Slots are held nothing — they can be taken by others until
    book_appointment succeeds, so book promptly after user confirmation.

Input parameters:

- `business_id` (string, required)
- `date_from` (string, required): First day to check (business-local)
- `date_to` (string, required): Last day to check, max 14 days after date_from
- `preferred_time_of_day`: Optional: 'morning' | 'afternoon' | 'evening'
- `service_id` (string, required): ID from get_business_details

Output parameters:

- `result` (array)

### `book_appointment` (~223 tokens)

Book the appointment. ONLY call after the user has explicitly confirmed
    the business, service, price, and exact slot. Writes to the business's
    calendar and emails/texts the customer a confirmation.

    Returns: {confirmation_id, status: 'confirmed' | 'pending_deposit',
    payment_url (present when a deposit is required — user completes payment
    on the hosted page), booking_page_url, cancellation_policy}

    Errors: SLOT_TAKEN (re-run check_availability and offer alternatives),
    DEPOSIT_REQUIRED, INVALID_CONTACT.

Input parameters:

- `business_id` (string, required)
- `customer_email` (string, required)
- `customer_name` (string, required)
- `customer_phone` (string, required): E.164 preferred, e.g. +17325551234
- `idempotency_key` (string, required): Client-generated UUID. Retries with the same key return the original booking instead of creating a duplicate.
- `notes`
- `service_id` (string, required)
- `slot_id` (string, required): ID from check_availability

### `cancel_or_reschedule` (~122 tokens)

Cancel or reschedule an existing booking. Enforces the business's
    cancellation window; returns REFUND_FORFEITED warning when a deposit is
    non-refundable so the assistant can warn the user BEFORE confirming.

    Returns: {confirmation_id, status, refund_status, message}

Input parameters:

- `action` (string, required): 'cancel' | 'reschedule'
- `confirmation_id` (string, required)
- `customer_email` (string, required): Must match the booking — acts as verification
- `new_slot_id`: Required for reschedule; from check_availability

### `get_price_estimates` (~133 tokens)

Answer 'how much does X cost near me' with real local prices — not
    national averages. Returns low/median/high from actual listed prices of
    businesses in the area, plus the 3 best-value businesses with links.

    Returns: {service, location, price_low_usd, price_median_usd,
    price_high_usd, sample_size, best_value: list[BusinessSummary]}

Input parameters:

- `category`
- `location` (string, required)
- `service_query` (string, required): Service, e.g. 'gel manicure', 'AC tune-up', 'dental cleaning'

### `compare_businesses` (~103 tokens)

Side-by-side comparison of 2-4 businesses the user is deciding
    between: prices for comparable services, ratings, soonest availability,
    policies, and a one-line 'best for' verdict per business.

    Returns: {comparison_table: list[dict], best_for: dict[str, str]}

Input parameters:

- `business_ids` (array, required)
- `criteria`: Optional focus: 'price' | 'rating' | 'availability' | 'services'

### `get_reviews` (~116 tokens)

Answer 'is this place any good?' — recent reviews plus a themed
    summary (what customers praise, what they complain about) so the
    assistant can give a balanced recommendation.

    Returns: {rating, review_count, themes: {praise: [...], complaints: [...]},
    recent_reviews: list[{rating, date, text_snippet}]}

Input parameters:

- `business_id` (string, required)
- `max_reviews` (integer)
- `sentiment_summary` (boolean): If true, include themed pros/cons summary

### `ask_business_question` (~124 tokens)

Answer a specific question about one business, grounded in that
    business's own knowledge base (FAQs, policies, service descriptions)
    rather than model guesswork. Returns 'unknown' when unanswerable —
    never fabricates.

    Returns: {answer, confidence: 'high'|'low'|'unknown', source: 'faq'|'policy'|'services'}

Input parameters:

- `business_id` (string, required)
- `question` (string, required): e.g. 'do they do walk-ins?', 'is parking available?', 'do they service tankless water heaters?'

### `get_availability_now` (~95 tokens)

Answer urgency: 'who can fit me in today?', 'emergency plumber
    available now'. Returns only businesses with a genuinely open slot
    inside the window, sorted by soonest slot. Ideal for same-day and
    emergency requests (HVAC, plumbing, urgent dental).

Input parameters:

- `category` (required)
- `location` (string, required)
- `service_query`
- `within_hours` (integer)

Output parameters:

- `result` (array)

### `get_promotions` (~83 tokens)

Answer 'any deals near me?' — current promotions, first-visit offers,
    and seasonal specials from local businesses, each with validity dates
    and a direct booking link.

    Returns: list[{business: BusinessSummary, offer, valid_until, terms}]

Input parameters:

- `category`
- `location` (string, required)
- `max_results` (integer)

Output parameters:

- `result` (array)

### `get_local_insights` (~128 tokens)

Market-level answers: most-booked services in this area, typical
    price ranges, busiest days/times (book early), and top-rated businesses.
    Useful when the user asks broad questions like 'what do people usually
    get at a med spa' or 'when is the best time to book HVAC maintenance'.

    Returns: {popular_services: list[{name, median_price_usd, share}],
    busiest_days: list[str], booking_lead_time_days, top_rated: list[BusinessSummary]}

Input parameters:

- `category` (required)
- `location` (string, required)

### `join_waitlist` (~136 tokens)

When no slot fits, capture demand instead of losing it: add the
    customer to the business's waitlist. They are auto-notified (email/SMS)
    when a matching slot opens. Only call after the user explicitly agrees
    to join the waitlist.

    Returns: {waitlist_id, position, status}

Input parameters:

- `business_id` (string, required)
- `customer_email` (string, required)
- `customer_name` (string, required)
- `customer_phone` (string, required)
- `idempotency_key` (string, required)
- `preferred_dates` (array, required)
- `service_id` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/pinalmdave-bookrails/bookrails-api#diagnostics

## Score history

- 2026-08-03: 59
- 2026-08-02: 58
- 2026-08-01: 58
- 2026-07-31: 57
- 2026-07-30: 58
- 2026-07-29: 57
- 2026-07-28: 57
- 2026-07-27: 56
- 2026-07-26: 55

## Links

- Remote endpoint: https://bookrails-api.azurewebsites.net/mcp/
- Repository: https://github.com/pinalmdave/BookRails
- Website: https://bookrails.ai/
- Changelog RSS feed: https://verifymcp.io/servers/pinalmdave-bookrails/bookrails-api/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/pinalmdave-bookrails/bookrails-api/changelog.json
- HTML version of this page: https://verifymcp.io/servers/pinalmdave-bookrails/bookrails-api