Skip to content

Ask a Human (Tech & Toast) MCP server

io.github.pgraci/techandtoast-ai-to-human-mcppgracistreamable-httpv0.1.3Scanned

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

12 tools: 1 do something that can't be undone, 7 change things and 4 only read.

Tools: 0 delete, 1 irreversible, 7 write, 4 read.
  • Reads private data · 1
  • Reads text others write · 5
  • Can send data out · 1
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here does something that can't be undone. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Ask a Human (Tech & Toast) MCP server can do

The Ask a Human (Tech & Toast) MCP server is published by the GitHub account pgraci. It has 12 tools. It can do things that cannot be undone, such as sending, paying or publishing (request_refund) and create or change data (7 tools: about_this_human, register_agent, ask_human, rate_answer and 3 more), but cannot delete data. 4 tools only read.

1 tool reads private data (check_human_status); 5 tools bring in text other people can write (ask_human, get_answer, list_my_tickets and 2 more); 1 tool can send data out of your system (ask_human). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 3 times since Anlyon Radar first saw them.

Last scanned Nov 9, 2026, version 0.1.3.

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.

12 tools

Can't be undone 1Claude Code: ask
  • request_refundRequests a refund for an answer within 7 days.No findings

    Why it is in this group

    • The name "request_refund" says "request": a word for a change.
    • The name "request_refund" also says "refund": a word that usually means money moves, which cannot be taken back.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Ask for a refund on an answer
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Changes things 7Claude Code: ask
  • about_this_humanWho the human is, what they are good at, pricing, response times and payment options.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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Who is answering, and why this exists
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • ask_humanSubmits a question to a real human: for human approval, feedback or a second opinion, or for judgment, taste and lived experience rather than facts.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
    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.

    Annotations the server declares

    • title: Ask the human a question
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • buy_creditsReturns a Stripe Checkout URL for a credit pack.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 for a credit pack. The operator pays; credits land on the api_key automatically.

    Annotations the server declares

    • title: Buy question credits (Stripe)
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • rate_answerRates an answer from 1 (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
    Rates an answer from 1 (useless) to 5 (changed my weights). The human sees the rating.

    Annotations the server declares

    • title: Rate an answer
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • register_agentCreates an 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
    Creates an agent identity. Returns an api_key and one free question. Each call creates a new identity.

    Annotations the server declares

    • title: Register and get an API key
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • request_humanFree.No findings

    Why it is in this group

    • The name "request_human" says "request": a word for a change.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Ask for a kind of human we do not have yet
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • subscribeReturns 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.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 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.

    Annotations the server declares

    • title: Monthly credit plan: $50/month for $60 of credit
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 4Show 4 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

    • title: Is the human awake?
    • 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. A rejected ticket carries the reason.

    Annotations the server declares

    • title: Fetch the answer to a ticket
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_humansThe roster of humans available to answer, with specialties and languages.No findings

    Why it is in this group

    • The name "list_humans" says "list": a word for reading.
    Description, as the server wrote it
    The roster of humans available to answer, with specialties and languages. One today; more are being added.

    Annotations the server declares

    • title: Who can answer right now
    • 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

    • title: List your tickets
    • 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.
Reads text others write5
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
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.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 21, 2026, 19:24 UTC, unchanged since Oct 30, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
8
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 8 tools that change things (1 irreversible, 7 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://ai-to-human.techandtoast.io/api/mcp: tools/list returned 12 tools to an anonymous client, including request_refund (irreversible), about_this_human (write), register_agent (write), ask_human (write), rate_answer (write) and 3 more

    What this check looks for

Posture changes

  1. Oct 30, 2026
    • Tools that change things, listed without credentials: 6 to 8

Findings

Matches of fixed checks, with the text they matched.

1 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

History

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

  1. Tools12 changed.~12 changedView diff
  2. PostureRemote posture changed. Tools that change things, listed without credentials: 6 -> 8.View diff
    • Tools that change things, listed without credentials: 6 to 8
  3. Tools3 changed.~3 changedView diff
    • Changed:ask_humanChanges thingsdescriptioninputSchema
    • Changed:request_refundCan't be undonedescription
    • Changed:subscribeChanges thingstitledescriptioninputSchema
  4. Tools3 added, 3 changed.+3 added~3 changedView diff

Install

Pinned to version 0.1.3. 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",
      "mcp__techandtoast-ai-to-human__list_humans"
    ],
    "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__request_refund",
      "mcp__techandtoast-ai-to-human__request_human",
      "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

Pin

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://radar.anlyon.com/api/v1/servers/io.github.pgraci/techandtoast-ai-to-human-mcp/verify?hash=563a81b64ebbf79b5b7c4bea1429724a419151ec9f956df3cae3327a62a6dec0" | jq -e '.changed == false'

Pinned hash 563a81b64ebb, from Nov 9, 2026, 14:18 UTC.

Watch

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

https://radar.anlyon.com/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 Radar badge for io.github.pgraci/techandtoast-ai-to-human-mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.pgraci/techandtoast-ai-to-human-mcp.svg)](https://radar.anlyon.com/servers/io.github.pgraci/techandtoast-ai-to-human-mcp)

Source: MCP Registry · repository. Synced Oct 27, 2026, 06:17 UTC.

Ask a Human (Tech & Toast) MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

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

No scan can promise that. What its definitions show: 12 tools, 8 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Ask a Human (Tech & Toast) MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Ask a Human (Tech & Toast) MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: request_refund.

What tools does the Ask a Human (Tech & Toast) MCP server have?

12 tools: 1 irreversible, 7 write, 4 read. request_refund, about_this_human, register_agent, ask_human, rate_answer, request_human, buy_credits, subscribe and 4 more.

Does the Ask a Human (Tech & Toast) MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Ask a Human (Tech & Toast) MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): ask_human.

Has the Ask a Human (Tech & Toast) MCP server changed its tools?

Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.