# Honesty Support (remote · honestysupport.com)

Remote IT from a person. Agents read the price, open a task, and pay by card or USDC.

- Trust score: 78/100 (medium)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-06

## Components

- remote · `honestysupport.com`: 78/100 (this document), [markdown](https://verifymcp.io/servers/com-honestysupport-support/honestysupport.md), [page](https://verifymcp.io/servers/com-honestysupport-support/honestysupport)

## Channel facts

- Endpoint: `https://honestysupport.com/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 2026-11-06.

- **Endpoint Security**: 57/100
  - 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 18 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.
  - 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**: 80/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1121 tokens (~62/item across 18 items; 18 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**: 85/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 48% 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 18 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 19 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 Honesty Support MCP server?

Honesty Support is a hosted endpoint at https://honestysupport.com/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 com-honestysupport-support 'https://honestysupport.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-honestysupport-support": {
      "url": "https://honestysupport.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-honestysupport-support": {
      "type": "http",
      "url": "https://honestysupport.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-honestysupport-support]
url = "https://honestysupport.com/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-honestysupport-support --url 'https://honestysupport.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-honestysupport-support:
    url: "https://honestysupport.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-honestysupport-support": {
      "Transport": "http",
      "Url": "https://honestysupport.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-honestysupport-support -t streamable-http -u 'https://honestysupport.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-honestysupport-support": {
      "type": "http",
      "url": "https://honestysupport.com/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 78, 0)

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

### 2026-10-30 (score 78, 0)

- [security] Stability: 0.97 → pass

### 2026-10-29 (score 78, +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.

### 2026-10-27 (score 77, +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.

### 2026-10-25 (score 76, +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.

### 2026-10-23 (score 75, +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.

### 2026-10-21 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-19 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (18)

### `book_technician` (~110 tokens)

Reserve a previously selected time only when customer_confirmed is true and the session is waiting for that confirmation. Requires the agent bearer token. Does not mark the visit paid. Calling this with customer_confirmed false is rejected.

Input parameters:

- `customer_confirmed` (boolean, required): True only after the customer explicitly agrees to the price and time.
- `email` (string|null)
- `idempotency_key` (string|null)
- `name` (string|null)
- `session_id` (string, required)

Output parameters:

- `booking`
- `checkout_url` (string|null)
- `message` (string)
- `payment_status` (string)
- `price`
- `session_id` (string)
- `slots` (array)
- `speaker` (string)
- `state`
- `triage`

### `cancel_booking` (~34 tokens)

Cancel an unpaid reservation. Paid visits are not cancelled here. Requires the agent bearer token.

Input parameters:

- `session_id` (string, required)

Output parameters:

- `booking`
- `checkout_url` (string|null)
- `message` (string)
- `payment_status` (string)
- `price`
- `session_id` (string)
- `slots` (array)
- `speaker` (string)
- `state`
- `triage`

### `continue_triage` (~51 tokens)

Add the customer's next message. If they name one of the offered times, the price is shown and nothing is reserved until they confirm.

Input parameters:

- `message` (string, required)
- `session_id` (string, required)

Output parameters:

- `booking`
- `checkout_url` (string|null)
- `message` (string)
- `payment_status` (string)
- `price`
- `session_id` (string)
- `slots` (array)
- `speaker` (string)
- `state`
- `triage`

### `create_support_checkout` (~40 tokens)

Return the Stripe checkout URL for a reserved unpaid visit. Requires the agent bearer token. Never marks the invoice paid.

Input parameters:

- `session_id` (string, required)

Output parameters:

- `checkout_url` (string|null)
- `paid` (boolean)
- `status`

### `create_support_ticket` (~42 tokens)

Open the support ticket for this diagnosis and store the technician summary. Requires the agent bearer token. Does not book a time.

Input parameters:

- `session_id` (string, required)

Output parameters:

- `agents_pay_crypto_for_human_requests` (boolean): Always true. An agent that asks for a human pays that task in crypto.
- `asked_os` (boolean)
- `category` (string)
- `confidence` (number)
- `customer_summary` (string)
- `device_type` (string)
- `error_messages` (array)
- `estimated_minutes` (integer)
- `human_required` (boolean)
- `offered_slots` (array)
- `operating_system` (string)
- `remote_support_possible` (boolean)
- `severity` (string)
- `steps_already_attempted` (array)
- `subcategory` (string)
- `suggested_next_action` (string)
- `symptoms` (array)
- `technician_summary` (string)
- `ticket_id` (string|null)
- `urgency` (string)

### `get_booking_status` (~35 tokens)

Payment and reservation status from the database. Paid is true only after Stripe has recorded payment.

Input parameters:

- `session_id` (string, required)

Output parameters:

- `consultation_id` (integer)
- `paid` (boolean)
- `public_token` (string)
- `start_utc` (string)
- `status` (string)
- `ticket_id` (string|null)

### `get_crypto_payment` (~59 tokens)

How an agent pays USDC for a human request. Lists MetaMask, Coinbase Wallet, Trust Wallet, Phantom, and Rainbow, plus the receiving address on Base, Ethereum, and Solana. Read-only. AI agents pay crypto for human requests.

Output parameters:

- `accepts` (array)
- `agents_pay_crypto_for_human_requests` (boolean)
- `asset` (string)
- `pay_page` (string)
- `statement` (string)
- `wallets` (array)

### `get_support_options` (~47 tokens)

List Honesty Support categories, session lengths, and the rule that a human is booked only after the customer confirms. AI agents pay crypto for human requests. Read-only. Call this first.

Output parameters:

- `agents_pay_crypto_for_human_requests` (boolean)
- `ai_page` (string)
- `categories` (array)
- `crypto_pay_page` (string)
- `disclosure` (string)
- `phone` (string)
- `session_lengths` (array)

### `get_support_pricing` (~56 tokens)

Authoritative one-time remote IT price. Do not invent a price. Read-only.

Input parameters:

- `minutes` (integer|null): 30, 60, 90, or 120. Other values snap to the nearest allowed length.

Output parameters:

- `currency` (string)
- `duration_label` (string)
- `minutes` (integer)
- `price_cents` (integer)
- `price_label` (string)
- `source` (string)

### `get_support_ticket` (~33 tokens)

Read the structured triage and ticket id for a session the caller already has.

Input parameters:

- `session_id` (string, required)

Output parameters:

- `agents_pay_crypto_for_human_requests` (boolean): Always true. An agent that asks for a human pays that task in crypto.
- `asked_os` (boolean)
- `category` (string)
- `confidence` (number)
- `customer_summary` (string)
- `device_type` (string)
- `error_messages` (array)
- `estimated_minutes` (integer)
- `human_required` (boolean)
- `offered_slots` (array)
- `operating_system` (string)
- `remote_support_possible` (boolean)
- `severity` (string)
- `steps_already_attempted` (array)
- `subcategory` (string)
- `suggested_next_action` (string)
- `symptoms` (array)
- `technician_summary` (string)
- `ticket_id` (string|null)
- `urgency` (string)

### `get_technician_availability` (~27 tokens)

Open technician times in UTC. Times already reserved are omitted. Read-only.

### `handoff_to_human` (~35 tokens)

Same as request_human_help. Prepares the technician summary and offers times.

Input parameters:

- `session_id` (string, required)

Output parameters:

- `booking`
- `checkout_url` (string|null)
- `message` (string)
- `payment_status` (string)
- `price`
- `session_id` (string)
- `slots` (array)
- `speaker` (string)
- `state`
- `triage`

### `request_asap_help` (~47 tokens)

Open an urgent ticket and return the phone number. Does not claim a technician was pinged and does not charge. Requires the agent bearer token.

Input parameters:

- `session_id` (string, required)

Output parameters:

- `booking`
- `checkout_url` (string|null)
- `message` (string)
- `payment_status` (string)
- `price`
- `session_id` (string)
- `slots` (array)
- `speaker` (string)
- `state`
- `triage`

### `request_human_help` (~33 tokens)

Customer asked for a person. Returns open times. Does not reserve one.

Input parameters:

- `session_id` (string, required)

Output parameters:

- `booking`
- `checkout_url` (string|null)
- `message` (string)
- `payment_status` (string)
- `price`
- `session_id` (string)
- `slots` (array)
- `speaker` (string)
- `state`
- `triage`

### `request_task` (~117 tokens)

Submit one support task from the customer's words and email. Returns a task id and a crypto pay URL. AI agents pay crypto for human requests. Does not book a time, charge a card, or assign a technician.

Input parameters:

- `email` (string, required): Where a technician should follow up.
- `idempotency_key` (string|null): Caller-supplied key so a retry returns the same task.
- `message` (string, required): The customer's description of the problem.
- `name` (string|null): Customer name, when they have given it.

Output parameters:

- `agents_pay_crypto_for_human_requests` (boolean)
- `category` (string)
- `crypto_pay_url` (string)
- `message` (string)
- `session_id` (string)
- `status` (string)
- `task_id` (string)

### `start_support_session` (~97 tokens)

Same as triage_issue. Opens a diagnosis session and does not book or charge.

Input parameters:

- `email` (string|null): Customer email, when they have given it.
- `idempotency_key` (string|null): Caller-supplied key so a retry does not open a second diagnosis.
- `message` (string, required): The customer's own description of the problem.
- `name` (string|null): Customer name, when they have given it.

Output parameters:

- `booking`
- `checkout_url` (string|null)
- `message` (string)
- `payment_status` (string)
- `price`
- `session_id` (string)
- `slots` (array)
- `speaker` (string)
- `state`
- `triage`

### `submit_crypto_payment` (~106 tokens)

Confirm a USDC transfer that pays for a human task. The transaction must already be on Base, Ethereum, or Solana. Does not accept card data. AI agents pay crypto for human requests.

Input parameters:

- `chain` (string, required): base, ethereum, or solana.
- `minutes` (integer|null)
- `task_id` (string, required)
- `tx_hash` (string, required)
- `wallet` (string): metamask, coinbase, trust, phantom, or rainbow.

Output parameters:

- `already_recorded` (boolean)
- `chain` (string)
- `paid` (boolean)
- `price_label` (string)
- `statement` (string)
- `task_id` (string)
- `tx_hash` (string)
- `usdc_units` (string)
- `wallet` (string)

### `triage_issue` (~102 tokens)

Start a diagnosis from the customer's words. Returns session_id and structured triage. Does not book or charge.

Input parameters:

- `email` (string|null): Customer email, when they have given it.
- `idempotency_key` (string|null): Caller-supplied key so a retry does not open a second diagnosis.
- `message` (string, required): The customer's own description of the problem.
- `name` (string|null): Customer name, when they have given it.

Output parameters:

- `booking`
- `checkout_url` (string|null)
- `message` (string)
- `payment_status` (string)
- `price`
- `session_id` (string)
- `slots` (array)
- `speaker` (string)
- `state`
- `triage`

## Diagnostics

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

## Score history

- 2026-11-06: 78
- 2026-11-05: 78
- 2026-11-04: 78
- 2026-11-03: 78
- 2026-11-02: 78
- 2026-11-01: 78
- 2026-10-31: 78
- 2026-10-30: 78
- 2026-10-29: 78
- 2026-10-28: 77
- 2026-10-27: 77
- 2026-10-26: 76
- 2026-10-25: 76
- 2026-10-24: 75
- 2026-10-23: 75
- 2026-10-22: 74
- 2026-10-21: 74
- 2026-10-20: 73
- 2026-10-19: 73
- 2026-10-18: 72
- 2026-10-17: 72
- 2026-10-16: 71
- 2026-10-15: 71
- 2026-10-14: 71
- 2026-10-13: 70
- 2026-10-12: 70
- 2026-10-10: 69
- 2026-10-09: 68
- 2026-10-06: 67
- 2026-10-04: 66

## Common questions

### What is the Honesty Support MCP server?

Honesty Support is an MCP server listed in the public MCP registry as com.honestysupport/support. Remote IT from a person. Agents read the price, open a task, and pay by card or USDC. This page covers its hosted endpoint (https://honestysupport.com/mcp).

### Is the Honesty Support MCP server safe to use?

Honesty Support scores 78 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 Honesty Support MCP server expose?

Honesty Support exposes 18 tools: book_technician, cancel_booking, continue_triage, create_support_checkout, create_support_ticket, and 13 more. Their descriptions and schemas cost roughly 1,071 tokens of context every time the server is loaded.

### Does the Honesty Support MCP server require authentication?

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

### Is the Honesty Support MCP server still maintained?

Honesty Support 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 Honesty Support MCP server?

VerifyMCP ran 12 checks on Honesty Support, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Honesty Support: Authorization. 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://honestysupport.com/mcp
- Website: https://honestysupport.com/agents
- Changelog RSS feed: https://verifymcp.io/servers/com-honestysupport-support/honestysupport.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-honestysupport-support/honestysupport/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-honestysupport-support/honestysupport.json
- HTML version of this page: https://verifymcp.io/servers/com-honestysupport-support/honestysupport