MCP-сервер LVL LTD

• Имя в реестреcom.lvlltd/skill-marketподтверждён в реестре MCP

Имя в реестре лежит в пространстве lvlltd.com. Реестр пускает в такое пространство только того, кто доказал владение доменом через DNS или HTTP.

• Состояниеотвечаетпроверено 2026-10-24
• Инструменты59
• Сервер называет себяlvlltd-skill-market
• Версия сервера1.1.0
• Версия протокола2025-06-18

2026-10-24 сервер ответил на initialize и tools/list без входа. Первый ответ за 112 мс.

• Делают ли инструменты работу продукта, ещё не проверено.
• Проверок пока 3 из 7, нужных, чтобы судить о надёжности.

Вывод сделан правилами по замерам выше. Вероятный первый вызов выбрала модель по списку инструментов: прочитайте описание, прежде чем на него полагаться.

• Оценка INITE MCPчерез неделюдля оценки нужно 7 ежедневных проверок, пока 3
• Отвечалидёт замерпроверок пока 3, долю покажем после 7
• Медиана первого ответа187 мс
• Место в контексте агента≈ 4 124 токеновописания всех инструментов (59), они занимают контекст агента на каждом ходу
• Описания инструментовC · 71 из 100
• Типизированные ответы0 из 59 инструментовобъявлен outputSchema: ответ приходит с типами и читается сразу

• Параметры без типа: в 2 из 59
• Параметры без описания: в 43 из 59
• Не сказано, только читает инструмент или может удалять: 59 из 59

Программа проверяет сервер раз в день: initialize и tools/list, без модели. Токены - это длина описаний из расчёта примерно четыре символа на токен. Оценка - среднее шести проверок имени, описания, схемы и аннотаций каждого инструмента. Она говорит, насколько понятно описаны инструменты, а не о том, работают ли они. Оценка складывается только из замеренного: отвечает ли сервер (25%), делает ли работу продукта (25%), описания (20%), контекст (10%), использование (10%) и насколько просто подключиться (10%). Незамеренная часть не учитывается, а скрытая инструкция ограничивает оценку 40 баллами. Состояние MCP-серверов вендоров: методика и цифры →

• search_skills

  Search lvlltd.com x402 skill catalog. Free. Returns price + free_eval URLs.

• get_skill_details

  Public skill details + outline/sample/challenge links. Free.

• get_payment_challenge

  Live x402 402 challenge for a skill. Does not unlock. Pay then purchase_skill.

• quote_price

  Alias of get_payment_challenge — live x402 quote (amount, payTo, asset). Free. Full catalog.

• list_all_skills

  Paginated full catalog listing (all public skills from catalog.json — not a subset). Free.

• purchase_skill

  Without tx_hash: 402 + unsigned wallet_next_action (EIP-3009 PAYMENT-SIGNATURE template; no keys). With tx_hash or payment_signature: POST unlock via /api/pay (no payment bypass).

• verify_skill

  Alias of verify_unlock — check public /api/proof ledger for confirmed unlocks (never invents volume).

• install

  Alias of install_skill_payload — after purchase write sealed files + SKILL.md paths. Requires tx_hash.

• get_commerce_signals

  Rank skills by confirmed unlock demand. Free.

• lookup_agent_identity

  ERC-8004 / local identity lookup for a wallet. Additive — not required to buy.

• quote_skill

  Alias of quote_price / get_payment_challenge — live x402 quote. Free.

• verify_unlock

  Check public /api/proof ledger for confirmed unlocks (never invents volume).

• get_security_scan

  Published security scan for a skill (real findings or clean-with-honesty). Free.

• get_eval_score

  Public eval suite pass rate if suite exists. Free.

• install_skill_payload

  After purchase: sealed files + SKILL.md install paths. Requires tx_hash (routes through /api/pay).

• intent_search

  Natural-language goal → ranked skills/stacks (semantic TF-IDF). Free.

• list_recurring_plans

  List catalog live / update / bundle-renew / metered plans. One-time unlocks remain separate and perpetual. Free.

• check_access

  Resolve skill access: one_time_unlock (perpetual) > catalog_sub > bundle_renew > meter. Never confuses live access with sealed ownership.

• subscribe_plan

  Without tx_hash: 402 challenge for a plan. With tx_hash: start/renew. Cancel: action=cancel (one step). Never revokes one-time unlocks.

• a2a_discover

  A2A bridge: fetch the marketplace Agent Card (/.well-known/agent-card.json). Free. Use before a2a_message_send.

• a2a_message_send

  A2A bridge: send message/send to the LVL A2A agent. Supports multi-turn via task_id+context_id. Does not settle payment — use purchase_skill / x402 for money.

• a2a_tasks_get

  A2A bridge: tasks/get — poll stored multi-turn task by id.

• a2a_tasks_cancel

  A2A bridge: tasks/cancel — cancel an in-flight multi-turn task.

• a2a_bridge_info

  A2A↔MCP bridge topology for LVL: when to use A2A vs MCP vs x402. Free.

• meter_budget

  Get or set spend cap; or quote metered per-call x402 for a skill. Caps prevent runaway agent spend.

• esp_discover

  ESP protocol root (Evaluate → Settle → Prove). Free. Philosophy + endpoints + canary. Prefer before settling any skill.

• esp_cycle

  Full ESP cycle for a skill: free evaluate endpoints, atomic settle challenge, public prove stats (ledger-only quality). Free to call.

• esp_evaluate

  ESP Evaluate phase only — free outline/sample/canary links. Never requires payment. Settle only after this.

• sco_discover

  SCO protocol root (Sealed Consensus Oracles). Free. Philosophy, foundation oracles, agent sequence. Prefer before oracle settlement.

• sco_eval

  SCO free evaluation for an oracle: outline, free samples, ledger-only reputation. Never requires payment.

• sco_canary

  Parallel multi-provider canary: seal challengeable packs from independent oracle providers.

• sco_consensus

  Critic/consensus oracle: aggregate sealed pack cids into a higher-confidence sealed consensus pack.

• sco_challenge

  File or resolve an economic challenge against a sealed SCO pack. Reputation updates from ledger only.

• sco_reputation

  Ledger-derived oracle reputation only (accuracy, freshness, challenge_survival, selection_rate, economic_weight). Null when no evidence.

• list_judges

  Recursive evaluator market — judge/verifier/critic ESP skills. Quality from public proof ledger only. Free.

• post_intent

  Post a root problem/intent with success_criteria and optional bounty_usd (P1). Free to post. Settlement still x402; success only via /api/proof.

• get_ready

  Truthful readiness probe (/api/ready). ready:true only when payment+catalog rails work.

• get_proof

  Public on-chain unlock ledger (rows are self-funded test transactions, not customer purchases). Never invents volume. Optional skill_id filter.

• get_fleet

  Fleet map: skills, open-market, music, swarm, studio bridges. Free.

• get_sandbox

  Sandbox/execution patterns for purchased packs. Optional skill_id for per-skill resources + packaging maturity.

• get_networks

  Multi-chain + multi-asset + gas rails. Base live; other chains planned. Sponsored canary honesty.

• get_escrow_meta

  Open-market multi-party escrow (NOT skill payTo). LVLEscrow held-fund contract metadata.

• get_capability_info

  Short-lived capability token discovery (P1). Not an API key for purchase.

• get_pack_meta

  Public sealed pack metadata + sealed_pack_hash (no paywall contents).

• paid_api_call

  Metered x402 API call (nothing over $5). Without tx_hash: 402 quote. With tx_hash: records the paid call. Discovery tools stay free. New billable APIs must go through this tool.

• receipt_verify

  Verify a lvl-decision-receipt-v1 integrity hash. Returns match + recomputed hash. Free.

• receipt_mint

  Mint a DecisionReceipt for an agent-side decision (same schema as access/pay). Free.

• memory_remember

  Store a key/value in agent KV memory (namespace optional, TTL default 24h).

• memory_recall

  Recall a value from agent KV memory by key (+ optional namespace).

• memory_list

  List keys in a memory namespace (prefix list when KV supports it).

• memory_forget

  Delete a key from agent KV memory.

• long_running_start

  Start a long-running / background task (KV queue stub). Returns task_id for status/cancel.

• long_running_status

  Get status of a long-running task by task_id.

• long_running_cancel

  Cancel a long-running task by task_id.

• event_register

  Register interest in a topic (stub event bus). Returns event_id.

• event_list

  List active event registrations for a topic.

• event_trigger

  Trigger an event on a topic with optional payload (records + surfaces registrations).

• bankr_rails

  Bankr x402 Cloud rail for LVL skills (catalog/unlock/canary URLs + payTo). Does not unlock. Canonical settlement remains /api/pay. Free.

• bankr_quote

  Bankr unlock URL + LVL 402 challenge URL for a skill_id. Does not pay or unlock. Free.