# RingGuard — AI Receptionist for Trade Businesses (remote · ringguard.online)

Missed-call cost, AI receptionist pricing and free trial signup; CRM tools for RingGuard sales reps

- Trust score: 91/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-06

## Components

- remote · `ringguard.online`: 91/100 (this document), [markdown](https://verifymcp.io/servers/online-ringguard-ringguard/ringguard.md), [page](https://verifymcp.io/servers/online-ringguard-ringguard/ringguard)

## Channel facts

- Endpoint: `https://ringguard.online/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.1.0`

## 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 2026-11-06.

- **Endpoint Security**: 94/100
  - 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.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 75/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1766 tokens (~84/item across 21 items; 21 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 77/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 32% 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 21 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 22 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 RingGuard — AI Receptionist for Trade Businesses MCP server?

RingGuard — AI Receptionist for Trade Businesses is a hosted endpoint at https://ringguard.online/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 online-ringguard-ringguard 'https://ringguard.online/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "online-ringguard-ringguard": {
      "url": "https://ringguard.online/mcp"
    }
  }
}
```

### VS Code

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

### Codex

```toml
[mcp_servers.online-ringguard-ringguard]
url = "https://ringguard.online/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add online-ringguard-ringguard --url 'https://ringguard.online/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  online-ringguard-ringguard:
    url: "https://ringguard.online/mcp"
```

### Netclaw

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

### Vellum

```bash
assistant mcp add online-ringguard-ringguard -t streamable-http -u 'https://ringguard.online/mcp'
```

### Other

```json
{
  "mcpServers": {
    "online-ringguard-ringguard": {
      "type": "http",
      "url": "https://ringguard.online/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.

### 2026-11-06 (score 91, 0)

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

### 2026-11-05 (score 91, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 90, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 89, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 88, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 87, +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.

### 2026-10-25 (score 86, +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.

### 2026-10-23 (score 85, +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 (21)

### `what_ringguard_does` (~60 tokens)

What RingGuard does

Explains RingGuard, the AI voice receptionist for trade businesses (HVAC, plumbing, roofing, towing): what it does, pricing, how it compares to a receptionist or answering service, and the free Shadow Trial. No sign-in needed.

### `missed_call_cost` (~137 tokens)

Missed-call cost calculator

Estimate how much revenue a business loses to unanswered calls, from its own call volume and average job value. No sign-in needed. Ask the user for their numbers rather than guessing them.

Input parameters:

- `avg_job_value` (number, required): Average revenue from one booked job, in dollars.
- `booking_percent` (number): Share of answered calls that become a booked job. Default 50 is an assumption.
- `calls_per_week` (number, required): Inbound calls the business gets in a typical week.
- `missed_percent` (number): Share of calls that go unanswered. Default 30 is an assumption; use the business's own figure if known.

### `ringguard_cost_estimate` (~85 tokens)

RingGuard cost estimate

Estimate what RingGuard would cost a business per month from how many calls it would handle, compared with a receptionist and an answering service. No sign-in needed.

Input parameters:

- `avg_call_minutes` (number): Average call length in minutes. Default 3 is an assumption.
- `calls_per_month` (integer, required): Calls RingGuard would answer per month (overflow + after-hours).

### `start_shadow_trial` (~166 tokens)

Start a free Shadow Trial

Sign a business up for RingGuard's free 48-hour Shadow Trial. The RingGuard team follows up by text or call within one business day. Only call this after the person has given their details and explicitly agreed to be contacted and to the privacy policy (https://ringguard.online/privacy). No sign-in needed.

Input parameters:

- `agreed_to_be_contacted` (boolean, required): Must be true: the person explicitly agreed to be contacted and to the privacy policy.
- `business_name` (string, required)
- `city` (string)
- `contact_name` (string, required)
- `email` (string, required)
- `industry` (string)
- `message` (string): Anything the business wants RingGuard to know.
- `phone` (string, required)
- `state` (string)

### `my_account` (~24 tokens)

My RingGuard account

Who is signed in to RingGuard, and a quick count of their pipeline.

### `find_leads` (~123 tokens)

Find leads

Search leads you can see: your own plus the unclaimed pool. Filter by name/phone text, status, industry, city or minimum lead score.

Input parameters:

- `city` (string)
- `industry` (string): Partial match, e.g. "hvac" or "dental".
- `limit` (integer)
- `min_score` (integer): Pipeline lead score, 1-5.
- `scope` (string)
- `search` (string): Text to match in business name, contact name or phone.
- `status` (string)

### `top_leads_to_call` (~66 tokens)

Top leads to call

The best leads to call right now: not yet won or lost, with a phone number, ranked by lead score and how much the open receptionist job is costing them. Includes the suggested cold-call angle.

Input parameters:

- `industry` (string)
- `limit` (integer)

### `lead_details` (~45 tokens)

Lead details

Everything about one lead: contact info, pitch (cold-call angle, Shadow Trial pitch, pain points), deal details, call history and notes.

Input parameters:

- `lead_id` (string, required)

### `claim_lead` (~69 tokens)

Claim a lead

Take an unclaimed lead from the shared pool into your own pipeline. Two-step: draft, then confirm.

Input parameters:

- `confirm` (boolean): Leave false to get a draft of the change. Only set true after the user has seen the draft and approved it.
- `lead_id` (string, required)

### `add_lead` (~126 tokens)

Add a lead

Add a new lead to your pipeline. Warns if another visible lead already has the same phone number. Two-step: draft, then confirm.

Input parameters:

- `business_name` (string, required)
- `city` (string)
- `confirm` (boolean): Leave false to get a draft of the change. Only set true after the user has seen the draft and approved it.
- `contact_name` (string)
- `email` (string)
- `industry` (string)
- `notes` (string)
- `phone` (string, required)
- `state` (string)

### `update_lead_status` (~74 tokens)

Update lead status

Move one of your leads to a new pipeline stage. Two-step: draft, then confirm.

Input parameters:

- `confirm` (boolean): Leave false to get a draft of the change. Only set true after the user has seen the draft and approved it.
- `lead_id` (string, required)
- `status` (string, required)

### `log_call` (~161 tokens)

Log a call

Record a call with one of your leads, optionally setting a follow-up. Some outcomes also move the lead's stage (won, trial_started, appointment_booked, not_interested, do_not_call). Two-step: draft, then confirm.

Input parameters:

- `confirm` (boolean): Leave false to get a draft of the change. Only set true after the user has seen the draft and approved it.
- `direction` (string)
- `follow_up_at` (string): When to follow up, as an ISO 8601 date-time with timezone, e.g. 2026-10-09T10:00:00-05:00.
- `lead_id` (string, required)
- `notes` (string)
- `outcome` (string, required)

### `my_follow_ups` (~35 tokens)

My follow-ups

Your leads with a follow-up due, including overdue ones, soonest first.

Input parameters:

- `days_ahead` (integer)

### `call_history` (~53 tokens)

Call history

Calls logged on one lead, or if no lead is given, the calls you logged in the last N days.

Input parameters:

- `days` (integer)
- `lead_id` (string)
- `limit` (integer)

### `new_trial_signups` (~48 tokens)

New Shadow Trial signups

Businesses that signed up for the free Shadow Trial on ringguard.online and haven't been converted to a lead yet.

Input parameters:

- `days` (integer)
- `include_converted` (boolean)

### `convert_trial_to_lead` (~74 tokens)

Convert trial signup to lead

Turn a Shadow Trial signup into a lead in your pipeline at the shadow_trial stage. Two-step: draft, then confirm.

Input parameters:

- `confirm` (boolean): Leave false to get a draft of the change. Only set true after the user has seen the draft and approved it.
- `trial_id` (string, required)

### `pipeline_report` (~38 tokens)

Pipeline report

Snapshot of your pipeline: leads by stage, won deals and monthly recurring revenue, follow-ups due, the unclaimed pool and open trial signups.

### `my_stats` (~35 tokens)

My call stats

Your call activity over the last N days: totals by outcome, conversations, trials started and wins.

Input parameters:

- `days` (integer)

### `team_leaderboard` (~34 tokens)

Team leaderboard

Owner only. Call activity per rep over the last N days, ranked by conversations.

Input parameters:

- `days` (integer)

### `lead_gen_status` (~42 tokens)

Lead-gen status

Health of the automated lead-gen pipeline (job postings → AI enrichment → unclaimed pool, runs every 4 hours): when it last delivered leads and how many.

### `undo_last_change` (~71 tokens)

Undo last change

Reverse the most recent change you made through Claude (claim, new lead, status change, logged call or trial conversion). Two-step: draft, then confirm.

Input parameters:

- `confirm` (boolean): Leave false to get a draft of the change. Only set true after the user has seen the draft and approved it.

## Diagnostics

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

## Score history

- 2026-11-06: 91
- 2026-11-05: 91
- 2026-11-04: 90
- 2026-11-03: 90
- 2026-11-02: 89
- 2026-11-01: 89
- 2026-10-31: 88
- 2026-10-30: 88
- 2026-10-29: 87
- 2026-10-28: 87
- 2026-10-27: 87
- 2026-10-26: 86
- 2026-10-25: 86
- 2026-10-24: 85
- 2026-10-23: 85
- 2026-10-22: 84
- 2026-10-21: 84
- 2026-10-20: 83
- 2026-10-19: 83
- 2026-10-18: 82
- 2026-10-17: 82
- 2026-10-16: 81
- 2026-10-15: 81
- 2026-10-14: 80
- 2026-10-13: 80
- 2026-10-12: 80
- 2026-10-10: 79
- 2026-10-09: 78
- 2026-10-07: 77

## Common questions

### What is the RingGuard — AI Receptionist for Trade Businesses MCP server?

RingGuard — AI Receptionist for Trade Businesses is an MCP server listed in the public MCP registry as online.ringguard/ringguard. Missed-call cost, AI receptionist pricing and free trial signup; CRM tools for RingGuard sales reps. This page covers its hosted endpoint (https://ringguard.online/mcp).

### Is the RingGuard — AI Receptionist for Trade Businesses MCP server safe to use?

RingGuard — AI Receptionist for Trade Businesses scores 91 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 RingGuard — AI Receptionist for Trade Businesses MCP server expose?

RingGuard — AI Receptionist for Trade Businesses exposes 21 tools: what_ringguard_does, missed_call_cost, ringguard_cost_estimate, start_shadow_trial, my_account, and 16 more. Their descriptions and schemas cost roughly 1,566 tokens of context every time the server is loaded.

### Does the RingGuard — AI Receptionist for Trade Businesses MCP server require authentication?

Yes. RingGuard — AI Receptionist for Trade Businesses 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 RingGuard — AI Receptionist for Trade Businesses MCP server still maintained?

RingGuard — AI Receptionist for Trade Businesses is still listed as active in the MCP registry. We last reached this channel on 6 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 RingGuard — AI Receptionist for Trade Businesses MCP server?

VerifyMCP ran 13 checks on RingGuard — AI Receptionist for Trade Businesses, 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://ringguard.online/mcp
- Website: https://ringguard.online/
- Changelog RSS feed: https://verifymcp.io/servers/online-ringguard-ringguard/ringguard.xml
- Changelog JSON feed: https://verifymcp.io/servers/online-ringguard-ringguard/ringguard/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/online-ringguard-ringguard/ringguard.json
- HTML version of this page: https://verifymcp.io/servers/online-ringguard-ringguard/ringguard