# Entervista (remote · entervista.ai)

Find and book local service businesses (plumbers, HVAC, detailers) at real prices, with approval.

- Trust score: 75/100 (medium)
- Change this week: +1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `entervista.ai`: 75/100 (this document), [markdown](https://verifymcp.io/servers/ai-entervista-entervista/entervista.md), [page](https://verifymcp.io/servers/ai-entervista-entervista/entervista)

## Channel facts

- Endpoint: `https://entervista.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 2026-11-05.

- **Endpoint Security**: 57/100
  - 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_request).
  - 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.
- **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 2040 tokens (~145/item across 14 items; 14 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 96/100
  - Stability check failed: schema churn in the 30 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 0 additions.
- **Tool Coverage**: 81/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 42% 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.
  - We read all 14 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

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

Entervista is a hosted endpoint at https://entervista.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-entervista-entervista 'https://entervista.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-entervista-entervista": {
      "url": "https://entervista.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-entervista-entervista": {
      "type": "http",
      "url": "https://entervista.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-entervista-entervista]
url = "https://entervista.ai/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add ai-entervista-entervista --url 'https://entervista.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-entervista-entervista:
    url: "https://entervista.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-entervista-entervista": {
      "Transport": "http",
      "Url": "https://entervista.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-entervista-entervista -t streamable-http -u 'https://entervista.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-entervista-entervista": {
      "type": "http",
      "url": "https://entervista.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.

### 2026-10-30 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 92 to 96.

### 2026-10-28 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 86 to 89.

### 2026-10-26 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 79 to 82.

### 2026-10-24 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 72 to 76.

### 2026-10-23 (score 71, 0)

- [security regression] Stability: 0.73 → fail
- [security regression] A breaking change shipped without a version bump: still 0.2.0
- [functional regression] “get_request_status” made “customer_token” required, so existing callers break

### 2026-10-20 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-18 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-16 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (14)

### `search_businesses` (~149 tokens)

Search businesses

Find businesses in the network by what the customer needs (e.g. 'plumber', 'smoothie', 'clogged sink'), optionally filtered by category, zip, location and open-now. Returns summaries with starting prices and whether they serve the zip.

Input parameters:

- `accepts` (string): Only businesses that support this action
- `category` (string): e.g. plumber, smoothies
- `lat` (number)
- `lng` (number)
- `open_now` (boolean)
- `q` (string): Free text: the need, a service, or a business name
- `zip` (string): Customer's 5-digit zip; results show serves_your_zip

### `get_business` (~60 tokens)

Get business profile

Full agent-readable profile: verified identity and license, services with real prices (what's included / excluded), hours, service zips, delivery rules, policies, and exactly how to act (order, quote, or book).

Input parameters:

- `slug` (string, required)

### `get_services` (~52 tokens)

List services

The business's services with pricing mode (fixed | starting_at | range | diagnostic_fee_then_quote | quote_required), price, what's included/excluded, and which intake fields are required.

Input parameters:

- `slug` (string, required)

### `check_service_area` (~70 tokens)

Check service area

Deterministic yes/no: does this business come to the customer's zip? Returns reason, the zips it serves, excluded zips, and alternative businesses when no.

Input parameters:

- `emergency` (boolean)
- `slug` (string, required)
- `zip` (string, required): Customer's 5-digit zip

### `get_service_requirements` (~63 tokens)

Get service requirements

Before creating a request: the exact questions to ask the customer for this service (required_fields / optional_fields, each with type and options), the pricing flow, and what happens next.

Input parameters:

- `service_sku` (string, required)
- `slug` (string, required)

### `place_service_request` (~487 tokens)

Place a service request

One call for any trade job (repair, quote, booking). Pass service_sku (or a plain description and it matches one), intake_answers keyed by the field ids from get_service_requirements, customer (name, phone, address with line1+zip), preferred_time, and slot_start only when the service flow asks for one. For an unchanged retry after receiving a receipt, include retry_ref and its customer_token with the original details. For quote-first requests without a slot, optionally generate and securely save intent_capability before the first submission; explicitly repeat the same business/details/capability to recover a lost first receipt. Do not silently resubmit. Without either capability this creates a separate request, even if the phone matches. A quote_required request is sent to the business without a price; a priced booking draft waits for the customer's approval. Follow the returned next_step, and never call a request booked until the business confirms.

Input parameters:

- `customer` (object, required): Who the job/order is for. Use what the customer already gave you; ask only for what a tool says is missing.
- `customer_token` (string): Customer token returned with retry_ref; only for an unchanged retry of that request.
- `description` (string): The problem in the customer's words; used to match a service if service_sku is omitted
- `intake_answers` (object)
- `intent_capability` (string): Optional secret 32-byte random client capability, encoded as lowercase hex. Save before sending a quote-first request without a slot; explicitly repeat unchanged details with the same capability to r…
- `notes` (string)
- `photos` (array): URLs (use upload_photo to turn an image into a URL)
- `preferred_time` (string): e.g. 'Tomorrow morning' or an ISO datetime
- `referred_by` (string): Slug of the business whose error response listed this one under referrals[] (its trusted partner). Lets both businesses see the referral.
- `retry_ref` (string): Existing request reference for an unchanged retry; requires customer_token. A phone number never authorizes a retry.
- `service_sku` (string)
- `slot_start` (string): ISO start from get_availability
- `slug` (string, required)
- `urgency` (string)

### `upload_photo` (~70 tokens)

Upload a photo of the problem

Stores an image and returns a URL to pass in photos[] of place_service_request. Some services require a photo (get_service_requirements says which).

Input parameters:

- `image_base64` (string, required)
- `media_type` (string): image/jpeg (default), image/png, image/webp, image/heic

### `get_availability` (~177 tokens)

Get availability

Live bookable windows over the next days, from the business's own schedule (hours, crew, jobs, holds, blocks). Pass service_sku to get windows sized for that service's duration and crew, plus: operating_state (open | closed | open_fully_booked | emergency_only | temporarily_unavailable | booking_future | unknown), confidence (verified | stale, with a note when not verified recently), earliest, the service's price and whether it auto-books or needs the owner. Use a slot's start with place_service_request or book_slot; the slot is held the moment the draft is created.

Input parameters:

- `date` (string): YYYY-MM-DD to start from
- `days` (number): 1 to 14, default 5
- `service_sku` (string)
- `slug` (string, required)

### `place_order` (~113 tokens)

Place an order

Draft an order (food/retail). Returns line items, total, a ref and a customer_token. Nothing reaches the business until approve_request. Ask the customer to confirm the total first.

Input parameters:

- `customer` (object, required): Who the job/order is for. Use what the customer already gave you; ask only for what a tool says is missing.
- `fulfillment` (string, required)
- `items` (array, required)
- `requested_time` (string): ISO datetime; omit for ASAP
- `slug` (string, required)

### `request_quote` (~146 tokens)

Request a quote

Ask a service business (plumber, etc.) for a price. Describe the problem in plain English. Many businesses answer instantly with an estimate and bookable slots; others reply within their stated response time (poll get_request_status).

Input parameters:

- `customer` (object, required): Who the job/order is for. Use what the customer already gave you; ask only for what a tool says is missing.
- `description` (string, required): What's wrong, in the customer's words
- `photos` (array): URLs
- `preferred_times` (array)
- `service_sku` (string): If the profile's service list clearly matches
- `slug` (string, required)
- `urgency` (string)

### `book_slot` (~104 tokens)

Book a fixed-price service

Book a flat-rate service (e.g. drain cleaning) into a slot from get_availability. Returns a draft awaiting the customer's approval.

Input parameters:

- `customer` (object, required): Who the job/order is for. Use what the customer already gave you; ask only for what a tool says is missing.
- `notes` (string)
- `service_sku` (string, required)
- `slot_start` (string, required): ISO start from get_availability
- `slug` (string, required)

### `approve_request` (~97 tokens)

Approve (customer said yes)

Use only after the customer explicitly approves the total / quote / final price. Sends it to the business. When offered_slots is present, pass the customer's chosen slot_start. If the business takes online payment, the result is status awaiting_payment with a payment_url: give that link to the customer; they pay on that page themselves.

Input parameters:

- `customer_token` (string, required)
- `ref` (string, required)
- `slot_start` (string)

### `get_request_status` (~48 tokens)

Get request status

Current status, ETA / arrival window, business response, and the next step. Poll this while waiting on a business.

Input parameters:

- `customer_token` (string, required)
- `ref` (string, required)

### `cancel_request` (~42 tokens)

Cancel a request

Cancel an order, quote or booking on the customer's behalf.

Input parameters:

- `customer_token` (string, required)
- `reason` (string)
- `ref` (string, required)

## Diagnostics

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

## Score history

- 2026-11-05: 75
- 2026-11-04: 75
- 2026-11-03: 75
- 2026-11-02: 75
- 2026-11-01: 75
- 2026-10-31: 75
- 2026-10-30: 75
- 2026-10-29: 74
- 2026-10-28: 74
- 2026-10-27: 73
- 2026-10-26: 73
- 2026-10-25: 72
- 2026-10-24: 72
- 2026-10-23: 71
- 2026-10-22: 71
- 2026-10-21: 71
- 2026-10-20: 71
- 2026-10-19: 70
- 2026-10-18: 70
- 2026-10-17: 69
- 2026-10-16: 69
- 2026-10-15: 68
- 2026-10-14: 68
- 2026-10-13: 67
- 2026-10-12: 67
- 2026-10-11: 67
- 2026-10-10: 66
- 2026-10-07: 65
- 2026-10-06: 64
- 2026-10-04: 63

## Common questions

### What is the Entervista MCP server?

Entervista is an MCP server listed in the public MCP registry as ai.entervista/entervista. Find and book local service businesses (plumbers, HVAC, detailers) at real prices, with approval. This page covers its hosted endpoint (https://entervista.ai/mcp).

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

Entervista scores 75 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 Entervista MCP server expose?

Entervista exposes 14 tools: search_businesses, get_business, get_services, check_service_area, get_service_requirements, and 9 more. Their descriptions and schemas cost roughly 1,678 tokens of context every time the server is loaded.

### Does the Entervista MCP server require authentication?

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

### Is the Entervista MCP server still maintained?

Entervista is still listed as active in the MCP registry. We last reached this channel on 5 November 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://entervista.ai/mcp
- Website: https://entervista.ai/developers
- Changelog RSS feed: https://verifymcp.io/servers/ai-entervista-entervista/entervista.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-entervista-entervista/entervista.json
- HTML version of this page: https://verifymcp.io/servers/ai-entervista-entervista/entervista