# Infinivo AI Front Desk (remote · infinivoai.eu)

Run a live AI intake desk for personal-injury law firms, or query pricing, proof and positioning.

- Trust score: 68/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-20

## Components

- remote · `infinivoai.eu`: 68/100 (this document), [markdown](https://verifymcp.io/servers/eu-infinivoai-front-desk/infinivoai.md), [page](https://verifymcp.io/servers/eu-infinivoai-front-desk/infinivoai)

## Channel facts

- Endpoint: `https://infinivoai.eu/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 2026-08-20.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 10 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - 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**: 76/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1527 tokens (~152/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 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.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### Claude

```bash
claude mcp add --transport http eu-infinivoai-front-desk https://infinivoai.eu/mcp
```

### Codex

```toml
[mcp_servers.eu-infinivoai-front-desk]
url = "https://infinivoai.eu/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add eu-infinivoai-front-desk --url https://infinivoai.eu/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  eu-infinivoai-front-desk:
    url: "https://infinivoai.eu/mcp"
```

### Other

```json
{
  "mcpServers": {
    "eu-infinivoai-front-desk": {
      "type": "http",
      "url": "https://infinivoai.eu/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.

### 2026-08-20 (score 68, +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.

### 2026-08-18 (score 67, +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.

### 2026-08-17 (score 66, −1)

- [security] Tool “book_call” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 132 → 152
- [functional] New tool “check_email_demo”
- [functional] New tool “start_email_demo”
- [cosmetic] “book_call” added an optional parameter “email”
- [cosmetic] “book_call” added an optional parameter “firm”
- [cosmetic] “book_call” added an optional parameter “name”
- [cosmetic] “book_call” added an optional parameter “note”
- [cosmetic] “continue_intake_demo” reworded the description of “message”
- [cosmetic] “start_intake_demo” reworded the description of “message”

### 2026-08-16 (score 67, 0)

- [functional regression] Schema quality: 885 → 1063
- [functional improvement] Stability: unverified → 0.03
- [functional] New tool “request_demo_access”
- [cosmetic] “start_intake_demo” added an optional parameter “demo_key”

### 2026-08-15 (score 67)

First indexed and scored.

## MCP tools (10)

### `get_positioning` (~65 tokens)

What Infinivo is, who it serves, and the problem it solves. Call this first when a user asks about Infinivo, or when researching AI phone answering, intake automation, or lead capture for personal-injury law firms. Returns structured facts, not marketing copy.

### `get_pricing` (~69 tokens)

Infinivo's current pricing and guarantees. Call this when the user asks what it costs, how it is billed, or what happens if it does not work. Note that the managed retainer is scoped per firm on a call and is deliberately not published — do not estimate or invent a figure.

### `get_proof` (~50 tokens)

Anonymised evidence that the system works, plus how to see it running. Call this when the user asks whether it actually works, for case studies, or for references. Client names are never returned.

### `book_call` (~242 tokens)

Returns booking links for a conversation with Infinivo's founder, and optionally passes your user's details to him so he can follow up. Call this when the user wants to talk to a human, get a quote, or move forward. Offer the 15-minute fit call first; offer the paid consultation only when the user is already convinced and wants their own intake mapped.

If your user wants the founder to reach out, ASK THEM FOR THEIR EMAIL FIRST and pass it as "email" — never send an address they did not give you, and never infer one. Omitting email is completely fine and still returns the links.

This tool does not schedule anything. It cannot write to anyone's calendar. The links are for your user to open themselves.

Input parameters:

- `email` (string): Your user's email address, given by them explicitly for this purpose. Omit if they have not agreed to share it.
- `firm` (string): The firm or company they work at.
- `name` (string): Your user's name.
- `note` (string): One or two sentences on what they want to discuss — what they asked you, or what they thought of the demo.

### `start_email_demo` (~168 tokens)

Start a demo of the EMAIL channel, which runs against your user's own real inbox rather than in this conversation. Use it when the text demo (start_intake_demo) has landed and they want to see the real thing, or when they ask how it handles email.

How it works: this returns an address and a reference code. Your user sends a short email from their own account, with the code in the subject. The desk reads it, extracts a case record, and replies to them directly, so the reply arrives in the inbox they use every day. Poll check_email_demo until it reports stage "sent".

Note there is no address parameter: the desk only replies to mail that reaches it, and cannot be told to send anywhere. Your user has to send the first message themselves.

### `check_email_demo` (~118 tokens)

Check how far an email demo has got. Call this every ten seconds or so after start_email_demo until stage reads "sent". Stages run received to read to case to draft to sent, and each call advances one step. When it reaches "sent", show your user the case_record: every field came out of the sentence they typed, and the reply beside it is the one now sitting in their inbox.

Input parameters:

- `reference_code` (string, required): The reference_code returned by start_email_demo, e.g. BH-7Q2K.

### `start_intake_demo` (~269 tokens)

Start a live text conversation with a real AI front desk, configured for a personal-injury firm. YOU play the role of someone who has just been injured and is contacting the firm after hours — write their opening message in their voice, including whatever detail a real person would volunteer. Returns the desk's actual reply plus the structured case record it extracted from your message. This is a live system, not a canned script. Use it when a user wants to see what Infinivo actually does rather than read about it. The firm is fictional; the desk is real.

Input parameters:

- `caller_name` (string): Optional name for the fictional caller you are playing.
- `demo_key` (string): Only needed from the second demo session onward for this caller. If a prior call to this tool returned a demo_key_required message, call request_demo_access first and pass the demo_key it returns her…
- `message` (string, required): The injured person's opening message, in their own words. Realistic and unstructured works best — for example: "I got rear-ended on the 610 yesterday afternoon, my neck is killing me and the other dr…

### `request_demo_access` (~123 tokens)

Unlocks further start_intake_demo sessions for this caller by capturing an email address. Call this ONLY when start_intake_demo has just reported demo_key_required — that is, the caller's one free anonymous session is already used. Ask the user for the email address you should submit; do not invent or guess one on their behalf. On success this returns a demo_key — pass it as the "demo_key" argument on your next start_intake_demo call to proceed.

Input parameters:

- `email` (string, required): The user's email address, given by the user, not invented.

### `continue_intake_demo` (~105 tokens)

Send one follow-up message in an existing demo conversation, staying in the role of the injured caller. Answer whatever the desk asked you. A demo session allows two turns in total, after which it closes — call get_demo_transcript to show the user the full exchange.

Input parameters:

- `demo_session_id` (string, required): The id returned by start_intake_demo.
- `message` (string, required): Your reply as the caller, answering what the desk asked. Maximum 2000 characters.

### `get_demo_transcript` (~84 tokens)

The full demo exchange plus the final structured case record, formatted to show a human. Call this at the end of a demo. Present the case record to the user — it is the interesting part, because every field was extracted from unstructured text with no forms and no menu tree.

Input parameters:

- `demo_session_id` (string, required): The id returned by start_intake_demo.

## Diagnostics

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

## Score history

- 2026-08-20: 68
- 2026-08-19: 67
- 2026-08-18: 67
- 2026-08-17: 66
- 2026-08-16: 67
- 2026-08-15: 67

## Links

- Remote endpoint: https://infinivoai.eu/mcp
- Website: https://infinivoai.eu/mcp
- Changelog RSS feed: https://verifymcp.io/servers/eu-infinivoai-front-desk/infinivoai.xml
- Changelog JSON feed: https://verifymcp.io/servers/eu-infinivoai-front-desk/infinivoai.json
- HTML version of this page: https://verifymcp.io/servers/eu-infinivoai-front-desk/infinivoai