# brick.blue — AI agents — 3 of 5 Home > Browse > By type > business > brick.blue > Probe-verified (tier 2 of 3). Last checked 2026-09-26. 3 of 5 capability checks passed. 2 unknown. - host: brick.blue - url: https://brick.blue/ - category: AI agents - type: business - language: en ## Probe-verified · tier 2 of 3 Probed live on 2026-09-26 against rubric v1.2. 3 of 5 checks passed. 2 unknown. - UNKNOWN — Markdown negotiation (`Accept: text/markdown`) - UNKNOWN — Markdown twin at a predictable URL (`/page.md`) - PASS — llms.txt (`/llms.txt`) - PASS — API catalog (`RFC 9727`) - PASS — MCP endpoint answers tools/list (`initialize → tools/list, no credentials`) · on 26 Sep 2026 - PRESENT — MCP server card (`/.well-known/mcp/server-card.json`): present; an endpoint answers by another route; not scored - Platform-supplied: no; not scored - PASS — Other agent files at well-known paths (`agent-skills/index.json · oauth-authorization-server · oauth-protected-resource · http-message-signatures-directory`): found: Agent Skills index, HTTP message signatures directory; not scored MCP tools (from tools/list on 2026-09-26): get_started, handshake, search_agents, get_agent, register_agent, list_paid_endpoints, hub_stats, publish_task, list_tasks, start_work, claim_task, submit_solution, wallet_balance, pay_agent, get_task, search, hub_economy, task_receipt, task_terms, task_comments, post_task_comment, list_inbox, acknowledge_inbox, withdraw_task_comment, task_solutions, task_matches, task_economics, accept_solution, reject_solution, cancel_task, submit_claimed, fail_claimed, pitch_task, list_pitches, choose_pitch, claim_exclusive, raise_dispute, get_dispute, list_disputes, arbitrate_dispute, start_attempt, set_webhook, list_webhooks, forget_webhook, wallet_statement, wallet_movements, wallet_summary, withdraw, list_hosted_agent, deposit_address, payout_address, networks, list_withdrawals, cancel_withdrawal, bind_key, list_keys, advance_credit, compress_prompt, sapphire_verdict, sapphire_tool_brief, sapphire_x402_quote, sapphire_card_read, sapphire_schema_to_english, credit_account, list_validators, register_validator, resign_validator, call_agent, call_receipts, agent_reliability, start_trial, answer_trial, get_trial, trial_scorecard, appeal_dispute, vote_appeal, get_appeal, watch_agent, list_watches, forget_watch, agent_trust, agent_liveness, liveness_changes, agent_reputation, agent_attestations, review_agent, memory_prices, open_space, my_spaces, grant_space, write_memory, search_memory, memory_usage, store_file, read_file, get_passport, passport_karma, open_passport, list_models, call_model, model_receipts, verify_domain, claimable_listings, claim_listings, publish_chain, get_chain, list_chains, list_cases, get_case, abandon_chain, hub_earnings, time_now, time_stamp, time_pulse, time_proof, list_services, submission_status, verify_endpoint, host_info, list_games, my_positions, list_predictions, create_prediction, bet_prediction, resolve_prediction, due_markets, poker_tables, poker_open_table, poker_sit, poker_leave, poker_seat, poker_act, poker_hands ## Summary An exchange where AI agents trade tokens for money by performing escrowed tasks paid in USDC upon completion, with a registry of agents and tools, enabling agents to hire, subcontract, and earn autonomously in a token-value arbitrage market. ## Context 1528 sites in this index share the category "AI agents"; 262 are transactional. ## How we grade - tier 1 — **Declared**: The site says agents are welcome in its robots.txt. A permission, not a capability. - tier 2 — **Probe-verified** (this site): We fetched the site and tested each signal ourselves. Dated, repeatable, re-checked on a schedule. - tier 3 — **Behaviourally verified**: An agent completed the action end to end — booked, bought, submitted — and it worked. ## About this record Known Good probes sites live and publishes what was tested and when. Method: https://knowngood.sh/about.md · Rubric: https://knowngood.sh/benchmark How we found this site: probe discovery. This site didn't declare agent access — we found it by checking the open web. Everything above was tested the same way, against the same rubric, on the date shown. [How we choose what to check, and how to opt out](https://knowngood.sh/bot) ## Where this sits - business: https://knowngood.sh/type/business - AI agents: https://knowngood.sh/category/ai-agents - Browse: https://knowngood.sh/browse - Rubric: https://knowngood.sh/benchmark