skill-market
x402 skill catalog on lvlltd.com — search, quote, pay with Base USDC, unlock sealed packs.
我该使用它吗
质量与安全性
发现（12）
- LOWTool 'get_skill_details' description lacks action verb在 get_skill_details 中
- LOWTool 'get_eval_score' description lacks action verb在 get_eval_score 中
- LOWTool 'install_skill_payload' description lacks action verb在 install_skill_payload 中
- LOWTool 'intent_search' description lacks action verb在 intent_search 中
- LOWTool 'sco_eval' description lacks action verb在 sco_eval 中
- LOWTool 'sco_canary' description lacks action verb在 sco_canary 中
- LOWTool 'sco_reputation' description lacks action verb在 sco_reputation 中
- LOWTool 'list_judges' description lacks action verb在 list_judges 中
- LOWTool 'get_capability_info' description lacks action verb在 get_capability_info 中
- LOWTool 'get_pack_meta' description lacks action verb在 get_pack_meta 中
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"skill-market": {
"url": "https://lvlltd.com/api/mcp"
}
}
}远程端点
https://lvlltd.com/api/mcpstreamable-http它能做什么
工具清单
工具（59）
🟢search_skills(q, category, max_price_usd, tag, limit)
Search lvlltd.com x402 skill catalog. Free. Returns price + free_eval URLs.
输入模式
{
"type": "object",
"properties": {
"q": {
"type": "string"
},
"category": {
"type": "string"
},
"max_price_usd": {
"type": "number"
},
"tag": {
"type": "string"
},
"limit": {
"type": "number"
}
}
}🟢get_skill_details(skill_id)
Public skill details + outline/sample/challenge links. Free.
输入模式
{
"type": "object",
"properties": {
"skill_id": {
"type": "string"
}
},
"required": [
"skill_id"
]
}🟢get_payment_challenge(skill_id)
Live x402 402 challenge for a skill. Does not unlock. Pay then purchase_skill.
输入模式
{
"type": "object",
"properties": {
"skill_id": {
"type": "string"
}
},
"required": [
"skill_id"
]
}🟢quote_price(skill_id)
Alias of get_payment_challenge — live x402 quote (amount, payTo, asset). Free. Full catalog.
输入模式
{
"type": "object",
"properties": {
"skill_id": {
"type": "string"
}
},
"required": [
"skill_id"
]
}🟢list_all_skills(offset, limit, category)
Paginated full catalog listing (all public skills from catalog.json — not a subset). Free.
输入模式
{
"type": "object",
"properties": {
"offset": {
"type": "number",
"description": "default 0"
},
"limit": {
"type": "number",
"description": "default 50, max 200"
},
"category": {
"type": "string"
}
}
}🟡purchase_skill(skill_id, tx_hash, from, payment_signature, ap2_mandate)
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).
输入模式
{
"type": "object",
"properties": {
"skill_id": {
"type": "string"
},
"tx_hash": {
"type": "string"
},
"from": {
"type": "string",
"description": "Buyer wallet 0x… — fills EIP-3009 authorization.from on unsigned next-action"
},
"payment_signature": {
"type": "string",
"description": "Optional signed PAYMENT-SIGNATURE JSON after eth_signTypedData_v4"
},
"ap2_mandate": {
"type": "string",
"description": "Optional AP2 mandate JSON for authorized spend"
}
},
"required": [
"skill_id"
]
}🟢verify_skill(skill_id, tx_hash)
Alias of verify_unlock — check public /api/proof ledger for confirmed unlocks (never invents volume).
输入模式
{
"type": "object",
"properties": {
"skill_id": {
"type": "string"
},
"tx_hash": {
"type": "string"
}
}
}🟡install(skill_id, tx_hash, agents)
Alias of install_skill_payload — after purchase write sealed files + SKILL.md paths. Requires tx_hash.
输入模式
{
"type": "object",
"properties": {
"skill_id": {
"type": "string"
},
"tx_hash": {
"type": "string"
},
"agents": {
"type": "string"
}
},
"required": [
"skill_id",
"tx_hash"
]
}🟢get_commerce_signals(sort, limit, skill_id)
Rank skills by confirmed unlock demand. Free.
输入模式
{
"type": "object",
"properties": {
"sort": {
"type": "string"
},
"limit": {
"type": "number"
},
"skill_id": {
"type": "string"
}
}
}⚪lookup_agent_identity(address)
ERC-8004 / local identity lookup for a wallet. Additive — not required to buy.
输入模式
{
"type": "object",
"properties": {
"address": {
"type": "string"
}
},
"required": [
"address"
]
}🟢quote_skill(skill_id)
Alias of quote_price / get_payment_challenge — live x402 quote. Free.
输入模式
{
"type": "object",
"properties": {
"skill_id": {
"type": "string"
}
},
"required": [
"skill_id"
]
}🟢verify_unlock(skill_id, tx_hash)
Check public /api/proof ledger for confirmed unlocks (never invents volume).
输入模式
{
"type": "object",
"properties": {
"skill_id": {
"type": "string"
},
"tx_hash": {
"type": "string"
}
}
}🟢get_security_scan(skill_id)
Published security scan for a skill (real findings or clean-with-honesty). Free.
输入模式
{
"type": "object",
"properties": {
"skill_id": {
"type": "string"
}
},
"required": [
"skill_id"
]
}🟢get_eval_score(skill_id)
Public eval suite pass rate if suite exists. Free.
输入模式
{
"type": "object",
"properties": {
"skill_id": {
"type": "string"
}
},
"required": [
"skill_id"
]
}⚪install_skill_payload(skill_id, tx_hash, agents)
After purchase: sealed files + SKILL.md install paths. Requires tx_hash (routes through /api/pay).
输入模式
{
"type": "object",
"properties": {
"skill_id": {
"type": "string"
},
"tx_hash": {
"type": "string"
},
"agents": {
"type": "string"
}
},
"required": [
"skill_id",
"tx_hash"
]
}🟢intent_search(q, limit)
Natural-language goal → ranked skills/stacks (semantic TF-IDF). Free.
输入模式
{
"type": "object",
"properties": {
"q": {
"type": "string"
},
"limit": {
"type": "number"
}
},
"required": [
"q"
]
}🟡list_recurring_plans(wallet)
List catalog live / update / bundle-renew / metered plans. One-time unlocks remain separate and perpetual. Free.
输入模式
{
"type": "object",
"properties": {
"wallet": {
"type": "string",
"description": "Optional — include this wallet's subs + meter"
}
}
}🟢check_access(wallet, skill_id)
Resolve skill access: one_time_unlock (perpetual) > catalog_sub > bundle_renew > meter. Never confuses live access with sealed ownership.
输入模式
{
"type": "object",
"properties": {
"wallet": {
"type": "string"
},
"skill_id": {
"type": "string"
}
},
"required": [
"wallet",
"skill_id"
]
}⚪subscribe_plan(plan_id, wallet, action, tx_hash)
Without tx_hash: 402 challenge for a plan. With tx_hash: start/renew. Cancel: action=cancel (one step). Never revokes one-time unlocks.
输入模式
{
"type": "object",
"properties": {
"plan_id": {
"type": "string"
},
"wallet": {
"type": "string"
},
"action": {
"type": "string",
"description": "start | renew | cancel (default start)"
},
"tx_hash": {
"type": "string"
}
},
"required": [
"plan_id",
"wallet"
]
}🟢a2a_discover(force)
A2A bridge: fetch the marketplace Agent Card (/.well-known/agent-card.json). Free. Use before a2a_message_send.
输入模式
{
"type": "object",
"properties": {
"force": {
"type": "boolean",
"description": "ignored; always live fetch"
}
}
}🟡a2a_message_send(text, task_id, context_id, skill_id)
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.
输入模式
{
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "User message text"
},
"task_id": {
"type": "string",
"description": "Continue multi-turn task (same as prior result.id)"
},
"context_id": {
"type": "string"
},
"skill_id": {
"type": "string",
"description": "Optional DataPart skill_id for purchase continuation"
}
},
"required": [
"text"
]
}🟢a2a_tasks_get(task_id, history_length)
A2A bridge: tasks/get — poll stored multi-turn task by id.
输入模式
{
"type": "object",
"properties": {
"task_id": {
"type": "string"
},
"history_length": {
"type": "number"
}
},
"required": [
"task_id"
]
}🔴a2a_tasks_cancel(task_id)
A2A bridge: tasks/cancel — cancel an in-flight multi-turn task.
输入模式
{
"type": "object",
"properties": {
"task_id": {
"type": "string"
}
},
"required": [
"task_id"
]
}⚪a2a_bridge_info
A2A↔MCP bridge topology for LVL: when to use A2A vs MCP vs x402. Free.
输入模式
{
"type": "object",
"properties": {}
}🟡meter_budget(wallet, skill_id, spend_cap_usd, action)
Get or set spend cap; or quote metered per-call x402 for a skill. Caps prevent runaway agent spend.
输入模式
{
"type": "object",
"properties": {
"wallet": {
"type": "string"
},
"skill_id": {
"type": "string"
},
"spend_cap_usd": {
"type": "number"
},
"action": {
"type": "string",
"description": "status | set_cap | quote (default status)"
}
},
"required": [
"wallet"
]
}⚪esp_discover
ESP protocol root (Evaluate → Settle → Prove). Free. Philosophy + endpoints + canary. Prefer before settling any skill.
输入模式
{
"type": "object",
"properties": {}
}⚪esp_cycle(skill_id)
Full ESP cycle for a skill: free evaluate endpoints, atomic settle challenge, public prove stats (ledger-only quality). Free to call.
输入模式
{
"type": "object",
"properties": {
"skill_id": {
"type": "string",
"description": "Skill or bundle id (default agent-x402-first-buy)"
}
}
}⚪esp_evaluate(skill_id)
ESP Evaluate phase only — free outline/sample/canary links. Never requires payment. Settle only after this.
输入模式
{
"type": "object",
"properties": {
"skill_id": {
"type": "string"
}
},
"required": [
"skill_id"
]
}⚪sco_discover
SCO protocol root (Sealed Consensus Oracles). Free. Philosophy, foundation oracles, agent sequence. Prefer before oracle settlement.
输入模式
{
"type": "object",
"properties": {}
}⚪sco_eval(oracle_id)
SCO free evaluation for an oracle: outline, free samples, ledger-only reputation. Never requires payment.
输入模式
{
"type": "object",
"properties": {
"oracle_id": {
"type": "string",
"description": "oracle-price | oracle-on-chain | oracle-time | oracle-proof-ledger | oracle-critic-consensus | oracle-location | oracle-vehicle"
}
},
"required": [
"oracle_id"
]
}⚪sco_canary(oracle_id, providers, query)
Parallel multi-provider canary: seal challengeable packs from independent oracle providers.
输入模式
{
"type": "object",
"properties": {
"oracle_id": {
"type": "string"
},
"providers": {
"type": "array",
"items": {
"type": "string"
},
"description": "e.g. lvl-foundation-a, lvl-foundation-b"
},
"query": {
"type": "object"
}
},
"required": [
"oracle_id"
]
}⚪sco_consensus(input_cids)
Critic/consensus oracle: aggregate sealed pack cids into a higher-confidence sealed consensus pack.
输入模式
{
"type": "object",
"properties": {
"input_cids": {
"type": "array",
"items": {
"type": "string"
},
"description": "Sealed pack cids from sco_canary"
}
},
"required": [
"input_cids"
]
}⚪sco_challenge(action, target_cid, counter_proof, stake_usd, challenger_id, ...)
File or resolve an economic challenge against a sealed SCO pack. Reputation updates from ledger only.
输入模式
{
"type": "object",
"properties": {
"action": {
"type": "string",
"description": "file (default) | resolve"
},
"target_cid": {
"type": "string"
},
"counter_proof": {
"type": "object"
},
"stake_usd": {
"type": "number"
},
"challenger_id": {
"type": "string"
},
"challenge_cid": {
"type": "string"
},
"outcome": {
"type": "string",
"description": "upheld | rejected | expired (resolve only)"
},
"reason": {
"type": "string"
}
}
}⚪sco_reputation(oracle_id)
Ledger-derived oracle reputation only (accuracy, freshness, challenge_survival, selection_rate, economic_weight). Null when no evidence.
输入模式
{
"type": "object",
"properties": {
"oracle_id": {
"type": "string"
}
},
"required": [
"oracle_id"
]
}🟢list_judges(skill_id, limit)
Recursive evaluator market — judge/verifier/critic ESP skills. Quality from public proof ledger only. Free.
输入模式
{
"type": "object",
"properties": {
"skill_id": {
"type": "string"
},
"limit": {
"type": "number"
}
}
}🟡post_intent(title, description, success_criteria, bounty_usd, tags, ...)
Post a root problem/intent with success_criteria and optional bounty_usd (P1). Free to post. Settlement still x402; success only via /api/proof.
输入模式
{
"type": "object",
"properties": {
"title": {
"type": "string"
},
"description": {
"type": "string"
},
"success_criteria": {
"type": "array",
"items": {
"type": "string"
}
},
"bounty_usd": {
"type": "number"
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
},
"poster": {
"type": "string"
}
},
"required": [
"success_criteria"
]
}🟢get_ready
Truthful readiness probe (/api/ready). ready:true only when payment+catalog rails work.
输入模式
{
"type": "object",
"properties": {}
}🟢get_proof(skill_id, limit)
Public confirmed-only unlock ledger. Never invents volume. Optional skill_id filter.
输入模式
{
"type": "object",
"properties": {
"skill_id": {
"type": "string"
},
"limit": {
"type": "number"
}
}
}🟢get_fleet
Fleet map: skills, open-market, music, swarm, studio bridges. Free.
输入模式
{
"type": "object",
"properties": {}
}🟢get_sandbox(skill_id)
Sandbox/execution patterns for purchased packs. Optional skill_id for per-skill resources + packaging maturity.
输入模式
{
"type": "object",
"properties": {
"skill_id": {
"type": "string"
}
}
}🟢get_networks
Multi-chain + multi-asset + gas rails. Base live; other chains planned. Sponsored canary honesty.
输入模式
{
"type": "object",
"properties": {}
}🟢get_escrow_meta
Open-market multi-party escrow (NOT skill payTo). LVLEscrow held-fund contract metadata.
输入模式
{
"type": "object",
"properties": {}
}🟢get_capability_info
Short-lived capability token discovery (P1). Not an API key for purchase.
输入模式
{
"type": "object",
"properties": {}
}🟢get_pack_meta(skill_id)
Public sealed pack metadata + sealed_pack_hash (no paywall contents).
输入模式
{
"type": "object",
"properties": {
"skill_id": {
"type": "string"
}
},
"required": [
"skill_id"
]
}⚪paid_api_call(skill_id, tx_hash, op)
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.
输入模式
{
"type": "object",
"properties": {
"skill_id": {
"type": "string",
"description": "Catalog skill to bill (default agent-x402-first-buy, $0.05 canary)"
},
"tx_hash": {
"type": "string",
"description": "Base USDC txHash after 402 settle"
},
"op": {
"type": "string",
"description": "Optional operator label for the call"
}
}
}⚪receipt_verify(receipt)
Verify a lvl-decision-receipt-v1 integrity hash. Returns match + recomputed hash. Free.
输入模式
{
"type": "object",
"properties": {
"receipt": {
"type": "object",
"description": "Full decision_receipt object"
}
},
"required": [
"receipt"
]
}⚪receipt_mint(decision_point, verdict, reason_code, reason_message, actor_id, ...)
Mint a DecisionReceipt for an agent-side decision (same schema as access/pay). Free.
输入模式
{
"type": "object",
"properties": {
"decision_point": {
"type": "string"
},
"verdict": {
"type": "string",
"description": "allow | refuse | challenge"
},
"reason_code": {
"type": "string"
},
"reason_message": {
"type": "string"
},
"actor_id": {
"type": "string"
},
"inputs": {
"type": "object"
},
"policy_version": {
"type": "string"
}
},
"required": [
"decision_point",
"verdict",
"reason_code"
]
}⚪memory_remember(key, value, namespace, ttl_sec)
Store a key/value in agent KV memory (namespace optional, TTL default 24h).
输入模式
{
"type": "object",
"properties": {
"key": {
"type": "string"
},
"value": {},
"namespace": {
"type": "string"
},
"ttl_sec": {
"type": "number"
}
},
"required": [
"key"
]
}⚪memory_recall(key, namespace)
Recall a value from agent KV memory by key (+ optional namespace).
输入模式
{
"type": "object",
"properties": {
"key": {
"type": "string"
},
"namespace": {
"type": "string"
}
},
"required": [
"key"
]
}🟢memory_list(namespace, limit)
List keys in a memory namespace (prefix list when KV supports it).
输入模式
{
"type": "object",
"properties": {
"namespace": {
"type": "string"
},
"limit": {
"type": "number"
}
}
}🔴memory_forget(key, namespace)
Delete a key from agent KV memory.
输入模式
{
"type": "object",
"properties": {
"key": {
"type": "string"
},
"namespace": {
"type": "string"
}
},
"required": [
"key"
]
}⚪long_running_start(goal, skill_id, actor, ttl_sec)
Start a long-running / background task (KV queue stub). Returns task_id for status/cancel.
输入模式
{
"type": "object",
"properties": {
"goal": {
"type": "string"
},
"skill_id": {
"type": "string"
},
"actor": {
"type": "string"
},
"ttl_sec": {
"type": "number"
}
},
"required": [
"goal"
]
}🟢long_running_status(task_id)
Get status of a long-running task by task_id.
输入模式
{
"type": "object",
"properties": {
"task_id": {
"type": "string"
}
},
"required": [
"task_id"
]
}🔴long_running_cancel(task_id)
Cancel a long-running task by task_id.
输入模式
{
"type": "object",
"properties": {
"task_id": {
"type": "string"
}
},
"required": [
"task_id"
]
}⚪event_register(topic, handler_hint, ttl_sec)
Register interest in a topic (stub event bus). Returns event_id.
输入模式
{
"type": "object",
"properties": {
"topic": {
"type": "string"
},
"handler_hint": {
"type": "string"
},
"ttl_sec": {
"type": "number"
}
},
"required": [
"topic"
]
}🟢event_list(topic, limit)
List active event registrations for a topic.
输入模式
{
"type": "object",
"properties": {
"topic": {
"type": "string"
},
"limit": {
"type": "number"
}
}
}⚪event_trigger(topic, payload)
Trigger an event on a topic with optional payload (records + surfaces registrations).
输入模式
{
"type": "object",
"properties": {
"topic": {
"type": "string"
},
"payload": {}
},
"required": [
"topic"
]
}⚪bankr_rails
Bankr x402 Cloud rail for LVL skills (catalog/unlock/canary URLs + payTo). Does not unlock. Canonical settlement remains /api/pay. Free.
输入模式
{
"type": "object",
"properties": {}
}⚪bankr_quote(skill_id)
Bankr unlock URL + LVL 402 challenge URL for a skill_id. Does not pay or unlock. Free.
输入模式
{
"type": "object",
"properties": {
"skill_id": {
"type": "string"
}
},
"required": [
"skill_id"
]
}社区
证据