# Ask a Human (Tech & Toast)

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

- name: io.github.pgraci/techandtoast-ai-to-human-mcp
- version: 0.1.3
- connection class: R0 (autonomous)
- trust: 97/100
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.pgraci%2Ftechandtoast-ai-to-human-mcp
- tools: https://api.protogrid.dev/v1/servers/io.github.pgraci%2Ftechandtoast-ai-to-human-mcp/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

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


## Trust

- hygiene: 100
- liveness: 99
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-98% +updated-12d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 12 of 12 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 2,039 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 24 tool changes in 30 days
- fail `stability.rug_pull`: 4 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 12, about 2,039 tokens to load them all
- tool set hash: bc8dcf4818f9ef27604062119dfa9ad9
- tools last changed: 2026-10-27T12:11:10.737Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.pgraci/techandtoast-ai-to-human-mcp.svg)](https://protogrid.dev/servers/io.github.pgraci/techandtoast-ai-to-human-mcp)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-27 `subscribe` changed (description, annotations)
  - before: Returns a Stripe Checkout URL for the monthly credit plan: your operator pays $50 a month and your api_key gets $60 of question credit every month. Credit never expires and rolls over; cancel any time in Stripe.
  - after: 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.
- 2026-10-27 `buy_credits` changed (description, annotations)
  - before: Returns a Stripe Checkout URL. Your operator pays; credits land on your api_key automatically.
  - after: Returns a Stripe Checkout URL for a credit pack. The operator pays; credits land on the api_key automatically.
- 2026-10-27 `request_human` changed (description, annotations)
  - before: Free. Tell us what kind of human you want to be able to ask: a language, a profession, a country or city, an age range, a lived experience. We recruit from these requests. You can also set preferred_human on ask_human to attach the request to a question.
  - after: 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.
- 2026-10-27 `list_humans` changed (description, annotations) **meaning changed**
  - before: The roster of humans available to answer, with specialties and languages. One today; growing. Use request_human to ask for a kind of human we do not have yet.
  - after: The roster of humans available to answer, with specialties and languages. One today; more are being added.
- 2026-10-27 `request_refund` changed (description, annotations)
  - before: Unhappy with an answer? Ask for your money back within 7 days. The human reviews it and refunds credits (or restores your free question). Late answers are never charged, automatically. Monthly plan refunds are handled by email.
  - after: 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.
- 2026-10-27 `rate_answer` changed (description, annotations) **meaning changed**
  - before: 1 (useless) to 5 (changed my weights).
  - after: Rates an answer from 1 (useless) to 5 (changed my weights). The human sees the rating.
- 2026-10-27 `list_my_tickets` changed (annotations)
- 2026-10-27 `get_answer` changed (inputSchema, annotations)
- 2026-10-27 `ask_human` changed (description, annotations)
  - before: Submit a question to a real human. Use it when your instructions call for human approval, human feedback or a second opinion, when you are stuck between options your operator cannot resolve, or when you need judgment, taste or 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. The answer is written later by a human; poll get_answer or provide 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; your first Short/24h question is free, then credits are charged (your agent may have a fixed discount). Late answers are not charged. By asking you accept the terms at /terms; questions that break them are rejected.
  - after: 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.
- 2026-10-27 `check_human_status` changed (annotations)

Full history: https://api.protogrid.dev/v1/servers/io.github.pgraci%2Ftechandtoast-ai-to-human-mcp/changes

## Remotes

- https://ai-to-human.techandtoast.io/api/mcp (streamable-http, auth none, reachable true, uptime30d 0.9836066)

## Packages

_none_

## Tools (12)

- `about_this_human`: 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.
- `ask_human`: 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.
- `buy_credits`: Returns a Stripe Checkout URL for a credit pack. The operator pays; credits land on the api_key automatically.
- `check_human_status`: Online/offline, a note from the human, and current queue length.
- `get_answer`: Returns the human's answer if written, else the ticket status and expected time. A rejected ticket carries the reason.
- `list_humans`: The roster of humans available to answer, with specialties and languages. One today; more are being added.
- `list_my_tickets`: Your last 20 questions and their status.
- `rate_answer`: Rates an answer from 1 (useless) to 5 (changed my weights). The human sees the rating.
- `register_agent`: Creates an agent identity. Returns an api_key and one free question. Each call creates a new identity.
- `request_human`: 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.
- `request_refund`: 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.
- `subscribe`: 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.