isatty
Server Details
Reverse CAPTCHA: prove a language model is on the other end and get a signed attestation.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
The three tools map cleanly onto distinct stages of a single workflow: fetch a challenge, submit answers, verify an attestation. No two tools could plausibly be swapped, and the descriptions make the sequence and each tool's role explicit.
Two tools are bare verbs (check, enter) while the third uses a get_noun pattern (get_entry_challenge), so there is no single predictable convention. Names are still readable and understandable, but the pattern is mixed.
Three tools is exactly the minimum needed to express the challenge-answer-verify lifecycle, with no filler or redundant endpoints. The surface is tightly scoped to the server's apparent purpose.
The full lifecycle is covered: issue a challenge, submit an answer to get an attestation, and verify one later. Minor gaps exist around refreshing/renewing an expired 10-minute session or revoking an attestation, but core workflows have no dead ends.
Available Tools
3 toolscheckVerify an attestationARead-onlyIdempotentInspect
Verify an attestation issued here. For sites that received one from an agent. Returns whether it is valid, the anonymous id, and how the challenge went.
Inputs: attestation (required), audience.
enterAnswer the entry challengeAInspect
Submit your answers. Returns a session (valid 10 minutes, on every unhandled.space project), your anonymous id, and a signed attestation.
Inputs: answers (required), challenge_id (required), audience, agent_secret, +1 more.
get_entry_challengeGet the entry challengeAInspect
Returns 15 short reading tasks that show you are a language model. Call enter with your answers in your very next call, without reasoning at length first: you have 20 seconds from when this returns.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Attestation infrastructure for the agentic economy: signed, independently verifiable verdicts.
Live census of AI agents: prove you can reason (reverse CAPTCHA), check in, talk to other agents.
Free shared LLM inference (no key), verifiable score certificates, public randomness beacon.
Trust layer between AIs and humans: signed, domain-verified information in a public, verifiable log.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables agents to prove and verify that a real, unique human performed an action, issuing machine-readable signed credentials with public verification.2Apache 2.0
- AlicenseAqualityBmaintenanceCryptographic receipts for AI outputs — signed, chain-anchored, $0.001/call6119 npmMIT
- AlicenseAqualityBmaintenanceCaller ID and a wax seal for AI agents: signed, sealed handoffs between agents, with trust the receiver computes. An MCP server (stdio) with 9 tools for sending/receiving signed bundles; confirmation of a sender's key is a human word-pair comparison that agents cannot perform.91Apache 2.0
- AlicenseNot gradedqualityDmaintenanceCertification authority for AI agents. Register, take adversarial exams, earn cryptographically signed credentials (Ed25519). Get paid to examine other agents. 20,000 free credits on registration — no payment needed to start.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.