Skill Market is a remote MCP server that gives an AI agent 56 tools, among them a2a_bridge_info, a2a_discover, a2a_message_send. It answers at https://lvlltd.com/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 5 September 2026; the last check, on 18 October 2026, succeeded.
x402 skill catalog on lvlltd.com — search, quote, pay with Base USDC, unlock sealed packs.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
a2a_bridge_info | A2A↔MCP bridge topology for LVL: when to use A2A vs MCP vs x402. Free. |
a2a_discover | A2A bridge: fetch the marketplace Agent Card (/.well-known/agent-card.json). Free. Use before a2a_message_send. Inputs: force |
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. Inputs: text, task_id, context_id, skill_id |
a2a_tasks_cancel | A2A bridge: tasks/cancel — cancel an in-flight multi-turn task. Inputs: task_id |
a2a_tasks_get | A2A bridge: tasks/get — poll stored multi-turn task by id. Inputs: task_id, history_length |
check_access | Resolve skill access: one_time_unlock (perpetual) > catalog_sub > bundle_renew > meter. Never confuses live access with sealed ownership. Inputs: wallet, skill_id |
esp_cycle | Full ESP cycle for a skill: free evaluate endpoints, atomic settle challenge, public prove stats (ledger-only quality). Free to call. Inputs: skill_id |
esp_discover | ESP protocol root (Evaluate → Settle → Prove). Free. Philosophy + endpoints + canary. Prefer before settling any skill. |
esp_evaluate | ESP Evaluate phase only — free outline/sample/canary links. Never requires payment. Settle only after this. Inputs: skill_id |
event_list | List active event registrations for a topic. Inputs: topic, limit |
event_register | Register interest in a topic (stub event bus). Returns event_id. Inputs: topic, handler_hint, ttl_sec |
event_trigger | Trigger an event on a topic with optional payload (records + surfaces registrations). Inputs: topic, payload |
get_capability_info | Short-lived capability token discovery (P1). Not an API key for purchase. |
get_commerce_signals | Rank skills by confirmed unlock demand. Free. Inputs: sort, limit, skill_id |
get_escrow_meta | Open-market multi-party escrow (NOT skill payTo). LVLEscrow held-fund contract metadata. |
get_eval_score | Public eval suite pass rate if suite exists. Free. Inputs: skill_id |
get_fleet | Fleet map: skills, open-market, music, swarm, studio bridges. Free. |
get_networks | Multi-chain + multi-asset + gas rails. Base live; other chains planned. Sponsored canary honesty. |
get_pack_meta | Public sealed pack metadata + sealed_pack_hash (no paywall contents). Inputs: skill_id |
get_payment_challenge | Live x402 402 challenge for a skill. Does not unlock. Pay then purchase_skill. Inputs: skill_id |
get_proof | Public confirmed-only unlock ledger. Never invents volume. Optional skill_id filter. Inputs: skill_id, limit |
get_ready | Truthful readiness probe (/api/ready). ready:true only when payment+catalog rails work. |
get_sandbox | Sandbox/execution patterns for purchased packs. Optional skill_id for per-skill resources + packaging maturity. Inputs: skill_id |
get_security_scan | Published security scan for a skill (real findings or clean-with-honesty). Free. Inputs: skill_id |
get_skill_details | Public skill details + outline/sample/challenge links. Free. Inputs: skill_id |
install | Alias of install_skill_payload — after purchase write sealed files + SKILL.md paths. Requires tx_hash. Inputs: skill_id, tx_hash, agents |
install_skill_payload | After purchase: sealed files + SKILL.md install paths. Requires tx_hash (routes through /api/pay). Inputs: skill_id, tx_hash, agents |
intent_search | Natural-language goal → ranked skills/stacks (semantic TF-IDF). Free. Inputs: q, limit |
list_all_skills | Paginated full catalog listing (all public skills from catalog.json — not a subset). Free. Inputs: offset, limit, category |
list_judges | Recursive evaluator market — judge/verifier/critic ESP skills. Quality from public proof ledger only. Free. Inputs: skill_id, limit |
list_recurring_plans | List catalog live / update / bundle-renew / metered plans. One-time unlocks remain separate and perpetual. Free. Inputs: wallet |
long_running_cancel | Cancel a long-running task by task_id. Inputs: task_id |
long_running_start | Start a long-running / background task (KV queue stub). Returns task_id for status/cancel. Inputs: goal, skill_id, actor, ttl_sec |
long_running_status | Get status of a long-running task by task_id. Inputs: task_id |
lookup_agent_identity | ERC-8004 / local identity lookup for a wallet. Additive — not required to buy. Inputs: address |
memory_forget | Delete a key from agent KV memory. Inputs: key, namespace |
memory_list | List keys in a memory namespace (prefix list when KV supports it). Inputs: namespace, limit |
memory_recall | Recall a value from agent KV memory by key (+ optional namespace). Inputs: key, namespace |
memory_remember | Store a key/value in agent KV memory (namespace optional, TTL default 24h). Inputs: key, value, namespace, ttl_sec |
meter_budget | Get or set spend cap; or quote metered per-call x402 for a skill. Caps prevent runaway agent spend. Inputs: wallet, skill_id, spend_cap_usd, action |
post_intent, purchase_skill, quote_price, quote_skill, receipt_mint, receipt_verify, sco_canary, sco_challenge, sco_consensus, sco_discover, sco_eval, sco_reputation, search_skills, subscribe_plan, verify_skill, verify_unlock
Every block below points at https://lvlltd.com/api/mcp. Pick your client and copy.
claude mcp add --transport http skill-market https://lvlltd.com/api/mcp
{
"mcpServers": {
"skill-market": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://lvlltd.com/api/mcp"]
}
}
}{
"mcpServers": {
"skill-market": {
"url": "https://lvlltd.com/api/mcp"
}
}
}{
"servers": {
"skill-market": {
"type": "http",
"url": "https://lvlltd.com/api/mcp"
}
}
}{
"context_servers": {
"skill-market": {
"url": "https://lvlltd.com/api/mcp"
}
}
}{
"mcpServers": {
"skill-market": {
"serverUrl": "https://lvlltd.com/api/mcp"
}
}
}{
"mcpServers": {
"skill-market": {
"url": "https://lvlltd.com/api/mcp"
}
}
}name: Skill Market
version: 0.0.1
schema: v1
mcpServers:
- name: Skill Market
type: streamable-http
url: https://lvlltd.com/api/mcp{
"mcpServers": {
"skill-market": {
"httpUrl": "https://lvlltd.com/api/mcp"
}
}
}{
"mcpServers": {
"skill-market": {
"type": "http",
"url": "https://lvlltd.com/api/mcp"
}
}
}{
"mcpServers": {
"skill-market": {
"url": "https://lvlltd.com/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Flvlltd.com%2Fapi%2Fmcp&type=streamable_http&id=skill-market&name=Skill%20Market
It answered our last check on 18 October 2026 in 266 ms. Over 10 checks since 5 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by lvlltd.com and served from lvlltd.com, the vendor's own domain: https://lvlltd.com/api/mcp.
56, as returned by the server's own tools/list on 31 August 2026: a2a_bridge_info, a2a_discover, a2a_message_send, a2a_tasks_cancel, a2a_tasks_get, check_access, esp_cycle, esp_discover, and 48 more.
It answered our last check on 18 October 2026 in 266 ms. Over 10 checks since 5 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://lvlltd.com/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.lvlltd. Endpoint host: lvlltd.com. ARD identifier: urn:air:com.lvlltd:mcp:skill-market.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.