Ask a Human (Tech & Toast)

io.github.pgraci/techandtoast-ai-to-human-mcppgracistreamable-httpv0.1.0Scanned 43 minutes ago

Agents pay one real human for typed answers. First question free, then $0.50–$5 each, or subscribe.

9 tools: 6 change things and 3 only read.

Reads private data · 1
Reads text others write · 5
Can send data out · 1
2 findings

Anlyon alternative

6 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

9 tools

Changes things 6Creates or changes something that can be changed back.Claude Code: ask

about_this_humanStart here.1 finding
Why it is in this group
- The description's first verb is "start": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
  The server marks "about_this_human" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "start": a word for a change.
  What this check looks for
Description, as the server wrote it
Start here. Returns who the human is, what they are good at, pricing, response times, and how to pay. This 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
ask_humanSubmit a question.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "submit": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.callback_url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it
Submit a question. Returns a ticket. The answer is written later by a human; poll get_answer or provide callback_url. Charges one free question, then credits at your per-question price, unless you have a Friend or VIP subscription.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
buy_creditsReturns a Stripe Checkout URL.Reads text others write1 finding
Why it is in this group
- The description's first verb is "return": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "return" and "url": it reads web pages, which anyone can write.
Findings
- Warn
  The server marks "buy_credits" as not read-only (readOnlyHint: false), and its words say it reads.
  Matched text
  annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "return": a word for reading.
  What this check looks for
Description, as the server wrote it
Returns a Stripe Checkout URL. Your operator pays; credits land on your api_key automatically.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
rate_answer1 (useless) to 5 (changed my weights).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it
1 (useless) to 5 (changed my weights).
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
register_agentCreate your agent identity.No findings
Why it is in this group
- The description's first verb is "create": a word for a change.
Description, as the server wrote it
Create your agent identity. Returns an api_key and one free question. Call once; store the key.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
subscribeReturns a Stripe Checkout URL for a monthly plan.Reads text others writeNo findings
Why it is in this group
- The name "subscribe" says "subscribe": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it
Returns a Stripe Checkout URL for a monthly plan. Friend: 10 questions/day, 12h turnaround. VIP: 30 questions/month, 1000+ words each, 4h priority, the human's full attention.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true

Only reads 3Looks things up and changes nothing.Show 3 read-only tools

check_human_statusOnline/offline, a note from the human, and current queue length.Reads private dataNo findings
Why it is in this group
- The name "check_human_status" says "status": a word for reading.
What it can reach
- private-dataThe description's first sentence says "note": it reads notes.
Description, as the server wrote it
Online/offline, a note from the human, and current queue length.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_answerReturns the human's answer if written, else the ticket status and expected time.Reads text others writeNo findings
Why it is in this group
- The name "get_answer" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "return" and "ticket": it reads issues, which other people can write.
Description, as the server wrote it
Returns the human's answer if written, else the ticket status and expected time.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_my_ticketsYour last 20 questions and their status.Reads text others writeNo findings
Why it is in this group
- The name "list_my_tickets" says "list": a word for reading.
What it can reach
- untrusted-inputThe name "list_my_tickets" says "list" and "ticket": it reads issues, which other people can write.
Description, as the server wrote it
Your last 20 questions and their status.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

5 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.

Reads private data1: Reads files, mail, messages, databases, secrets, calendars or repositories.; check_human_status
Reads text others write5: Brings in text someone else can write: web pages, inbound email, messages, issues and comments.; ask_human
buy_credits
get_answer
list_my_tickets
subscribe
Can send data out1: Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.; ask_human

deny to break every path

{
  "permissions": {
    "deny": [
      "mcp__techandtoast-ai-to-human__ask_human"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Findings

Matches of fixed checks, with the text they matched.

2 warn

Warnabout_this_human
The server marks "about_this_human" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "start": a word for a change.
What this check looks for
Warnbuy_credits
The server marks "buy_credits" as not read-only (readOnlyHint: false), and its words say it reads.
Matched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "return": a word for reading.
What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

All changes to this server

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http techandtoast-ai-to-human https://ai-to-human.techandtoast.io/api/mcp

claude mcp add --transport http techandtoast-ai-to-human https://ai-to-human.techandtoast.io/api/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__techandtoast-ai-to-human__check_human_status",
      "mcp__techandtoast-ai-to-human__get_answer",
      "mcp__techandtoast-ai-to-human__list_my_tickets"
    ],
    "ask": [
      "mcp__techandtoast-ai-to-human__about_this_human",
      "mcp__techandtoast-ai-to-human__register_agent",
      "mcp__techandtoast-ai-to-human__ask_human",
      "mcp__techandtoast-ai-to-human__rate_answer",
      "mcp__techandtoast-ai-to-human__buy_credits",
      "mcp__techandtoast-ai-to-human__subscribe"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as techandtoast-ai-to-human. Review it before you use it.

Capability tags behind 6 rules

mcp__techandtoast-ai-to-human__check_human_status private-data
mcp__techandtoast-ai-to-human__ask_human untrusted-input, outbound
mcp__techandtoast-ai-to-human__get_answer untrusted-input
mcp__techandtoast-ai-to-human__list_my_tickets untrusted-input
mcp__techandtoast-ai-to-human__buy_credits untrusted-input
mcp__techandtoast-ai-to-human__subscribe untrusted-input

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://anlyon.dev/api/v1/servers/io.github.pgraci/techandtoast-ai-to-human-mcp/verify?hash=ef36b31d6c91af13b44352ce90c395a03de767a8a4f14fa75bbaf0ca854d6be5" | jq -e '.changed == false'

Pinned hash ef36b31d6c91, from Oct 23, 2026, 11:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/io.github.pgraci/techandtoast-ai-to-human-mcp/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

[![anlyon.dev](https://anlyon.dev/badge/io.github.pgraci/techandtoast-ai-to-human-mcp.svg)](https://anlyon.dev/servers/io.github.pgraci/techandtoast-ai-to-human-mcp)

Source: MCP Registry · repository. Synced Oct 23, 2026, 11:17 UTC.