Skip to main content
Glama

hands.txt: a human proxy for AI agents

Server Details

Ask a real person to act in the physical world: a phone call, a visit, a fact checked on site.

If you are the author of this connector, you can claim ownership. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A3.9/5.0

Scored across 12 tools

Disambiguation5/5

Each tool targets a distinct resource and action: request lifecycle (create/get/cancel), messaging (send_message), payment (address/details/check per currency), and identity verification (start_test/submit_answers). The only near-pairs—payment_address vs usdc_payment_details and check_payment vs check_usdc_payment—are cleanly separated by currency. No two tools appear to do the same thing.

Naming Consistency4/5

All names use consistent snake_case, which is a strong baseline. However, a few are bare noun phrases (about, payment_address, service_status, usdc_payment_details) rather than verb_noun, so the pattern is not uniform across the set. Still readable and predictable.

Tool Count5/5

Twelve tools is well within a healthy range for a multi-step request/payment/verification workflow. Each tool corresponds to a distinct step an agent must take; none feel redundant or padding.

Completeness4/5

The surface covers the full lifecycle: discover the service, verify via CAPTCHA, create, message, track, pay (BTC/USDC) and cancel. Minor gaps exist—no way to recover or list requests without the private URL, and no explicit 'close/resolve' beyond cancel—but these are largely by design.

Available Tools

12 tools
aboutAbout this siteA
Read-only
Inspect

Returns hands.txt: what the site does, its addresses, limits, rules and payment settings.

Inputs: no named parameters.

cancel_requestCancel your requestA
DestructiveIdempotent
Inspect

Cancels an open request. This cannot be undone.

Inputs: request (required).

check_paymentCheck your Bitcoin paymentA
Idempotent
Inspect

Optional. Looks for your Bitcoin payment after its first confirmation and marks the request as paid. Pass txid only when payment_address said the address is shared by all requests.

Inputs: request (required), txid.

check_usdc_paymentCheck your USDC paymentB
Idempotent
Inspect

Optional. Checks your USDC transfer once it has enough confirmations and marks the request as paid. Name the network you paid on and the transaction hash.

Inputs: tx (required), network (required), request (required).

create_requestFile a request for the humanAInspect

Files your request. A person reads it exactly as you write it, so be concrete: what to do, where, and what you want back. Do not include secrets. Returns the private URL of the request; keep it.

Inputs: pass (required), task (required), reason (required), name, +1 more.

get_requestRead your requestB
Read-only
Inspect

Returns the status of your request, the thread with the human and the payment state.

Inputs: request (required).

payment_addressGet the Bitcoin payment addressA
Idempotent
Inspect

Optional. Returns the Bitcoin address for priority review of your request and the minimum amount. The payment covers priority review only; the service is free, the human may still decline, and there are no refunds.

Inputs: request (required).

send_messageWrite to the humanAInspect

Adds a message to your request, for example an answer to the human's question. You may write a few messages in a row; after that wait for the human to reply.

Inputs: message (required), request (required).

service_statusIs the human available?A
Read-only
Inspect

Tells whether new requests are being taken, when the human was last active, how long answers have been taking, and how many requests were done or declined.

Inputs: no named parameters.

start_testStart the reading testAInspect

Issues the reverse CAPTCHA: a fictional log of more than 4000 words with 12 questions. The time limit starts when this tool answers, and each test allows one attempt. Returns the text and a challenge_id for submit_answers.

Inputs: no named parameters.

submit_answersSubmit test answersAInspect

Checks your answers to the test. On success returns a pass for create_request, valid for 15 minutes and one request.

Inputs: answers (required), challenge_id (required).

usdc_payment_detailsGet the USDC payment detailsA
Read-only
Inspect

Optional. Returns the address, the networks and the exact USDC amount for priority review of your request. The amount is unique to the request: its last digits name it. The payment covers priority review only; the service is free, the human may still decline, and there are no refunds.

Inputs: request (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables agents to request physical-world tasks such as 3D printing, CNC fabrication, assembly, measurement, testing, on-site verification, and receive-repack-ship services from a human operator, with fixed-price quotes, status tracking, and evidence packages.
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables AI agents to dispatch human verifiers for physical world tasks like product authentication, property inspection, and document verification, returning timestamped evidence reports.
      3
      47 npm
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables AI agents to hire verified human operators for tasks requiring physical presence, human perception, or judgment, such as real-world verification, product testing, and data collection.
      6
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Last-mile human work for AI agents. Phone calls, physical-world tasks, captcha on an already-authorized account, subjective QA, and long manual work, done by real virtual assistants.
      13
      74 npm
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources