# com.lvlltd/skill-market (remote · lvlltd.com)

x402 skill catalog on lvlltd.com — search, quote, pay with Base USDC, unlock sealed packs.

- Trust score: 52/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-09

## Components

- remote · `lvlltd.com`: 52/100 (this document), [markdown](https://verifymcp.io/servers/com-lvlltd-skill-market/api-mcp.md), [page](https://verifymcp.io/servers/com-lvlltd-skill-market/api-mcp)

## Channel facts

- Endpoint: `https://lvlltd.com/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.5.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-09.

- **Endpoint Security**: 66/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 31 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 27/100
  - 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (poor).
  - Tool/resource definitions use about 1688 tokens (~52/item across 32 items; 31 tools + 1 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 72/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 16% of tool parameters carry a description.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add --transport http com-lvlltd-skill-market https://lvlltd.com/api/mcp
```

### Codex

```toml
[mcp_servers.com-lvlltd-skill-market]
url = "https://lvlltd.com/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-lvlltd-skill-market": {
      "type": "remote",
      "url": "https://lvlltd.com/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-lvlltd-skill-market --url https://lvlltd.com/api/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-lvlltd-skill-market:
    url: "https://lvlltd.com/api/mcp"
```

### Other

```json
{
  "mcpServers": {
    "com-lvlltd-skill-market": {
      "type": "http",
      "url": "https://lvlltd.com/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-09 (score 52)

First indexed and scored.

## MCP tools (31)

### `search_skills` (~66 tokens)

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

Input parameters:

- `category` (string)
- `limit` (number)
- `max_price_usd` (number)
- `q` (string)
- `tag` (string)

### `get_skill_details` (~29 tokens)

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

Input parameters:

- `skill_id` (string, required)

### `get_payment_challenge` (~37 tokens)

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

Input parameters:

- `skill_id` (string, required)

### `quote_price` (~40 tokens)

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

Input parameters:

- `skill_id` (string, required)

### `list_all_skills` (~60 tokens)

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

Input parameters:

- `category` (string)
- `limit` (number): default 50, max 200
- `offset` (number): default 0

### `purchase_skill` (~69 tokens)

Without tx_hash: payment_required 402 payload. With tx_hash: POST unlock via existing /api/pay (no payment bypass).

Input parameters:

- `ap2_mandate` (string): Optional AP2 mandate JSON for authorized spend
- `skill_id` (string, required)
- `tx_hash` (string)

### `verify_skill` (~46 tokens)

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

Input parameters:

- `skill_id` (string)
- `tx_hash` (string)

### `install` (~51 tokens)

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

Input parameters:

- `agents` (string)
- `skill_id` (string, required)
- `tx_hash` (string, required)

### `get_commerce_signals` (~42 tokens)

Rank skills by confirmed unlock demand. Free.

Input parameters:

- `limit` (number)
- `skill_id` (string)
- `sort` (string)

### `lookup_agent_identity` (~36 tokens)

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

Input parameters:

- `address` (string, required)

### `quote_skill` (~33 tokens)

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

Input parameters:

- `skill_id` (string, required)

### `verify_unlock` (~41 tokens)

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

Input parameters:

- `skill_id` (string)
- `tx_hash` (string)

### `get_security_scan` (~35 tokens)

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

Input parameters:

- `skill_id` (string, required)

### `get_eval_score` (~28 tokens)

Public eval suite pass rate if suite exists. Free.

Input parameters:

- `skill_id` (string, required)

### `install_skill_payload` (~54 tokens)

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

Input parameters:

- `agents` (string)
- `skill_id` (string, required)
- `tx_hash` (string, required)

### `intent_search` (~38 tokens)

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

Input parameters:

- `limit` (number)
- `q` (string, required)

### `list_recurring_plans` (~52 tokens)

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

Input parameters:

- `wallet` (string): Optional — include this wallet's subs + meter

### `check_access` (~54 tokens)

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

Input parameters:

- `skill_id` (string, required)
- `wallet` (string, required)

### `subscribe_plan` (~82 tokens)

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

Input parameters:

- `action` (string): start | renew | cancel (default start)
- `plan_id` (string, required)
- `tx_hash` (string)
- `wallet` (string, required)

### `meter_budget` (~73 tokens)

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

Input parameters:

- `action` (string): status | set_cap | quote (default status)
- `skill_id` (string)
- `spend_cap_usd` (number)
- `wallet` (string, required)

### `list_oracles` (~66 tokens)

List Oracle Rails (kind=oracle ESP skills). Free. Same discovery path as skills — free eval sacred, reputation from proof ledger only.

Input parameters:

- `live` (boolean): If true, only live/beta
- `priority` (string): P0 | P1 | P2

### `oracle_free_eval` (~57 tokens)

Free-evaluate an oracle (capped sample). Sacred free path — no payment. Returns sealed sample pack (not ledger-recorded).

Input parameters:

- `oracle_id` (string, required)
- `query` (object): Optional; defaults to sample_query

### `oracle_challenge` (~36 tokens)

x402 402 challenge for a sealed oracle result. Free. Pay then oracle_settle.

Input parameters:

- `oracle_id` (string, required)

### `oracle_settle` (~63 tokens)

Without tx_hash: payment_required 402. With tx_hash: settle → sealed attested result + proof ledger (kind=oracle). No payment bypass.

Input parameters:

- `oracle_id` (string, required)
- `query` (object)
- `tx_hash` (string)

### `oracle_result` (~47 tokens)

Re-download content-addressed sealed oracle result by cid for independent re-verification.

Input parameters:

- `cid` (string, required)
- `oracle_id` (string, required)
- `tx_hash` (string)

### `esp_discover` (~29 tokens)

ESP protocol root — free-eval → settle → prove invariants + completion layer URLs. Free.

### `esp_cycle` (~54 tokens)

Full ESP cycle for a skill (evaluate/settle/prove descriptors). Free. Never invents quality.

Input parameters:

- `phase` (string): optional evaluate|settle|prove|cycle
- `skill_id` (string, required)

### `memory_discover` (~49 tokens)

Sealed memory rails discovery + free-eval meta. Full value requires settle. Free for discovery/eval.

Input parameters:

- `cid` (string)
- `phase` (string): evaluate for free meta

### `graph_create` (~56 tokens)

Create ESP capability graph from intent (free-eval canaries → settle → prove). Free create.

Input parameters:

- `budget_usd_max` (number)
- `intent_text` (string, required)
- `risk_tier_max` (string)

### `graph_advance` (~77 tokens)

Advance capability graph: tick|free_eval|settle|prove|replan|fail_node|kill.

Input parameters:

- `action` (string, required)
- `graph_id` (string, required)
- `node_id` (string)
- `reason` (string)
- `skill_id` (string)
- `tx_hash` (string)

### `challenge_file` (~99 tokens)

File economic challenge against any sealed cid with counter-proof. Without payment returns 402 stake challenge.

Input parameters:

- `challenger_id` (string)
- `claim` (string)
- `counter_proof_type` (string)
- `dev` (boolean)
- `stake_usd` (number)
- `target_cid` (string, required)
- `target_kind` (string)
- `tx_hash` (string): or use dev:true for smoke

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-lvlltd-skill-market/api-mcp#diagnostics

## Score history

- 2026-08-09: 52

## Links

- Remote endpoint: https://lvlltd.com/api/mcp
- Repository: https://github.com/lvlltd/lvlltd-agent-marketplace
- Website: https://lvlltd.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-lvlltd-skill-market/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-lvlltd-skill-market/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-lvlltd-skill-market/api-mcp