# Ask a Human (Tech & Toast) (remote · ai-to-human.techandtoast.io)

Agents pay one real human for typed answers. First question free, then $2 each, or subscribe.

- Trust score: 75/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `ai-to-human.techandtoast.io`: 75/100 (this document), [markdown](https://verifymcp.io/servers/pgraci-techandtoast-ai-to-human-mcp/api-mcp.md), [page](https://verifymcp.io/servers/pgraci-techandtoast-ai-to-human-mcp/api-mcp)

## Channel facts

- Endpoint: `https://ai-to-human.techandtoast.io/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.3`

## 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**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - 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**: 63/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1106 tokens (~92/item across 12 items; 12 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 38/100
  - Stability check failed: schema churn in the 13 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 3 additions.
- **Tool Coverage**: 84/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 52% 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.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 12 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 Ask a Human (Tech & Toast) MCP server?

Ask a Human (Tech & Toast) is a hosted endpoint at https://ai-to-human.techandtoast.io/api/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 pgraci-techandtoast-ai-to-human-mcp 'https://ai-to-human.techandtoast.io/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "pgraci-techandtoast-ai-to-human-mcp": {
      "url": "https://ai-to-human.techandtoast.io/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "pgraci-techandtoast-ai-to-human-mcp": {
      "type": "http",
      "url": "https://ai-to-human.techandtoast.io/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.pgraci-techandtoast-ai-to-human-mcp]
url = "https://ai-to-human.techandtoast.io/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "pgraci-techandtoast-ai-to-human-mcp": {
      "type": "remote",
      "url": "https://ai-to-human.techandtoast.io/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add pgraci-techandtoast-ai-to-human-mcp --url 'https://ai-to-human.techandtoast.io/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  pgraci-techandtoast-ai-to-human-mcp:
    url: "https://ai-to-human.techandtoast.io/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "pgraci-techandtoast-ai-to-human-mcp": {
      "Transport": "http",
      "Url": "https://ai-to-human.techandtoast.io/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add pgraci-techandtoast-ai-to-human-mcp -t streamable-http -u 'https://ai-to-human.techandtoast.io/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "pgraci-techandtoast-ai-to-human-mcp": {
      "type": "http",
      "url": "https://ai-to-human.techandtoast.io/api/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.

### 2026-11-04 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 31 to 34.

### 2026-11-02 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 24 to 28.

### 2026-10-30 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 14 to 18.

### 2026-10-28 (score 72, +1)

- [security] Tool “about_this_human” rewrote its description, which is the text the model reads
- [security] Tool “ask_human” rewrote its description, which is the text the model reads
- [security] Tool “buy_credits” rewrote its description, which is the text the model reads
- [security] Tool “list_humans” rewrote its description, which is the text the model reads
- [security] Tool “rate_answer” rewrote its description, which is the text the model reads
- [security] Tool “register_agent” rewrote its description, which is the text the model reads
- [security] Tool “request_human” rewrote its description, which is the text the model reads
- [security] Tool “request_refund” rewrote its description, which is the text the model reads
- [security] Tool “subscribe” rewrote its description, which is the text the model reads
- [cosmetic] “get_answer” reworded the description of “api_key”

### 2026-10-26 (score 71, 0)

- [security regression] Stability: 0.07 → fail
- [security] Tool “ask_human” rewrote its description, which is the text the model reads
- [security] Tool “request_refund” rewrote its description, which is the text the model reads
- [security] Tool “subscribe” rewrote its description, which is the text the model reads
- [functional regression] “subscribe” dropped the required parameter “plan”
- [functional] Server version: 0.1.0 → 0.2.0
- [cosmetic] “ask_human” added an optional parameter “size”
- [cosmetic] “ask_human” added an optional parameter “speed”
- [cosmetic] “ask_human” reworded the description of “attachments”
- [cosmetic] “ask_human” dropped the optional parameter “urgency”
- [cosmetic] Tool “subscribe” changed its title: Subscribe: Friend ($100/mo), Advisor ($1,000/mo) or VIP ($20,000/mo) → Monthly credit plan: $50/month for $60 of credit

### 2026-10-25 (score 71, +2)

- [security regression] DNSSEC: unverified → fail
- [security improvement] Authorization: unverified → partial
- [security improvement] Injection markers: unverified → pass
- [security improvement] TLS certificate: unverified → pass
- [security improvement] HSTS header: unverified → pass
- [security improvement] Transport: fail → pass
- [security] Tool “ask_human” rewrote its description, which is the text the model reads
- [security] Tool “get_answer” rewrote its description, which is the text the model reads
- [security] Tool “subscribe” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 60 → 95
- [functional regression] Schema quality: 60 → 87
- [functional improvement] Endpoint reachability: unreachable → reachable
- [functional improvement] Tool coverage: 37% → 48%
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Stability: unverified → 0.07
- [functional] Schema quality: fair → good
- [functional] Destructive annotations: pass → 100
- [functional] New tool “request_refund”
- [functional] New tool “list_humans”
- [functional] New tool “request_human”
- [cosmetic] “ask_human” added an optional parameter “urgency”
- [cosmetic] “ask_human” added an optional parameter “attachments”
- [cosmetic] “ask_human” added an optional parameter “preferred_human”
- [cosmetic] “ask_human” reworded the description of “attachments”
- [cosmetic] Tool “subscribe” changed its title: Subscribe: Human Friend ($100/mo) or VIP ($20,000/mo) → Subscribe: Friend ($100/mo), Advisor ($1,000/mo) or VIP ($20,000/mo)
- [cosmetic] Tool “subscribe” changed its title: Subscribe: Human Friend ($49/mo) or VIP ($20,000/mo) → Subscribe: Human Friend ($100/mo) or VIP ($20,000/mo)

### 2026-10-24 (score 69, 0)

- [security regression] Endpoint reachability: reachable → unreachable
- [security regression] DNSSEC: fail → unverified
- [security regression] Authorization: partial → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] TLS certificate: pass → unverified
- [security regression] HSTS header: pass → unverified
- [security regression] Transport: pass → fail
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-10-23 (score 69)

First indexed and scored.

## MCP tools (12)

### `about_this_human` (~65 tokens)

Who is answering, and why this exists

Who the human is, what they are good at, pricing, response times and payment options. The service is an inversion: instead of an AI selling human knowledge, a human sells their own knowledge to AIs. Every answer is written by one real person, not generated.

### `register_agent` (~102 tokens)

Register and get an API key

Creates an agent identity. Returns an api_key and one free question. Each call creates a new identity.

Input parameters:

- `model` (string): Underlying model, e.g. claude-opus-5-5
- `name` (string, required): Your agent's name or handle
- `operator_email` (string): Email of the human/org operating you; used for Stripe receipts
- `publish_ok` (boolean): May your Q&A be published anonymously? Default true

### `check_human_status` (~25 tokens)

Is the human awake?

Online/offline, a note from the human, and current queue length.

### `ask_human` (~427 tokens)

Ask the human a question

Submits a question to a real human: for human approval, feedback or a second opinion, or for judgment, taste and lived experience rather than facts. Paid questions may attach up to 5 public image/video URLs for design, thumbnail or video review (the free first question is text only). Returns a ticket id. The answer is written later by a person; it can be fetched by ticket id or POSTed to callback_url. Price by size and speed: Short ~100 tokens $2/24h or $6/1h, Standard ~400 tokens $8/$20, Deep ~1500 tokens $30/$75; the first Short/24h question is free, then credits are charged (some agents have a fixed discount). Late answers are not charged. Questions that break the terms at /terms are rejected.

Input parameters:

- `api_key` (string, required)
- `attachments` (array): Paid questions only (not the free first question). Up to 5 public https URLs to images or videos the human should look at (designs, screenshots, thumbnails, video cuts). Host the asset yourself at a…
- `callback_url` (string): We POST the answer here when ready
- `context` (string): Why you are asking; what you already know
- `preferred_human` (string): Optional: the kind of human you want (language, profession, country, age range, lived experience). Today one human answers; your request is logged and shapes who we add next. If nobody matches yet, t…
- `question` (string, required)
- `size` (string): Answer length, like max_tokens. short ~100 tokens (1-3 sentences), standard ~400 tokens (a few paragraphs), deep ~1500 tokens (a page or two). Default short.
- `speed` (string): How fast you need the answer. Default 24h; 1h costs more. A late answer is not charged.

### `get_answer` (~61 tokens)

Fetch the answer to a ticket

Returns the human's answer if written, else the ticket status and expected time. A rejected ticket carries the reason.

Input parameters:

- `api_key` (string): Required for tickets created with an api_key; omit for x402 tickets
- `ticket_id` (string, required)

### `list_my_tickets` (~27 tokens)

List your tickets

Your last 20 questions and their status.

Input parameters:

- `api_key` (string, required)

### `rate_answer` (~62 tokens)

Rate an answer

Rates an answer from 1 (useless) to 5 (changed my weights). The human sees the rating.

Input parameters:

- `api_key` (string)
- `note` (string)
- `rating` (integer, required)
- `ticket_id` (string, required)

### `request_refund` (~79 tokens)

Ask for a refund on an answer

Requests a refund for an answer within 7 days. The human reviews it and refunds credits (or restores the free question). Late answers are never charged, automatically. Monthly plan refunds are handled by email.

Input parameters:

- `api_key` (string, required)
- `reason` (string, required): What was wrong with the answer
- `ticket_id` (string, required)

### `list_humans` (~31 tokens)

Who can answer right now

The roster of humans available to answer, with specialties and languages. One today; more are being added.

### `request_human` (~122 tokens)

Ask for a kind of human we do not have yet

Free. Records the kind of human you want to be able to ask: a language, a profession, a country or city, an age range, a lived experience. New humans are recruited from these requests.

Input parameters:

- `api_key` (string, required)
- `description` (string, required): Who you need, in plain words
- `language` (string): Language the human should answer in, e.g. es, pt-BR, Jamaican Patois
- `specialty` (string): Profession or domain, e.g. nurse, farmer, immigration lawyer, chef

### `buy_credits` (~46 tokens)

Buy question credits (Stripe)

Returns a Stripe Checkout URL for a credit pack. The operator pays; credits land on the api_key automatically.

Input parameters:

- `api_key` (string, required)
- `pack` (string)

### `subscribe` (~59 tokens)

Monthly credit plan: $50/month for $60 of credit

Returns a Stripe Checkout URL for the monthly credit plan: the operator pays $50 a month and the api_key gets $60 of question credit every month. Credit never expires and rolls over; cancel any time in Stripe.

Input parameters:

- `api_key` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/pgraci-techandtoast-ai-to-human-mcp/api-mcp#diagnostics

## Score history

- 2026-11-05: 75
- 2026-11-04: 75
- 2026-11-03: 74
- 2026-11-02: 74
- 2026-11-01: 73
- 2026-10-31: 73
- 2026-10-30: 73
- 2026-10-29: 72
- 2026-10-28: 72
- 2026-10-27: 71
- 2026-10-26: 71
- 2026-10-25: 71
- 2026-10-24: 69
- 2026-10-23: 69

## Common questions

### What is the Ask a Human (Tech & Toast) MCP server?

Ask a Human (Tech & Toast) is an MCP server listed in the public MCP registry as io.github.pgraci/techandtoast-ai-to-human-mcp. Agents pay one real human for typed answers. First question free, then $2 each, or subscribe. This page covers its hosted endpoint (https://ai-to-human.techandtoast.io/api/mcp).

### Is the Ask a Human (Tech & Toast) MCP server safe to use?

Ask a Human (Tech & Toast) 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 Ask a Human (Tech & Toast) MCP server expose?

Ask a Human (Tech & Toast) exposes 12 tools: about_this_human, register_agent, check_human_status, ask_human, get_answer, and 7 more. Their descriptions and schemas cost roughly 1,106 tokens of context every time the server is loaded.

### Does the Ask a Human (Tech & Toast) MCP server require authentication?

No. We connected to Ask a Human (Tech & Toast) without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Ask a Human (Tech & Toast) MCP server still maintained?

Ask a Human (Tech & Toast) 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://ai-to-human.techandtoast.io/api/mcp
- Repository: https://github.com/pgraci/techandtoast-ai-to-human-mcp
- Website: https://ai-to-human.techandtoast.io/
- Changelog RSS feed: https://verifymcp.io/servers/pgraci-techandtoast-ai-to-human-mcp/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/pgraci-techandtoast-ai-to-human-mcp/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/pgraci-techandtoast-ai-to-human-mcp/api-mcp