MCP server providing paid web tools (web_search, news_search, scrape, geocode, nlp, email_verify, convert, qr, feed, sitemap) that charge per call in USDC on Base via x402 protocol with user-controlled wallet
This server exposes 10 tools from an external package (superhighway-mcp) without visible schema definitions in the provided source. Tool names are action-oriented (web_search, scrape, geocode) but descriptions are minimal (10-30 chars, well below the 50-200 char baseline for LLM-optimized descriptions). No input schemas are visible for most tools except web_search and scrape, which show partial schemas. Parameter descriptions are absent or trivial. No output schemas documented. Error handling guidance is not evident. The examples show integration patterns but do not reveal the actual tool definitions, making it impossible to verify schema completeness, parameter validation, or error recovery patterns.
Convert between units or formats
Verify email address validity
Fetch and parse RSS/Atom feeds
Geocode a location query to coordinates
Search for news articles
Natural language processing operations
Generate QR codes
Scrape content from a URL
Tool definitions are external (superhighway-mcp package) and not visible in source. Cannot verify input schemas, parameter descriptions, output schemas, or error handling. Per HARD SCORING RULES, tools without visible schemas score 0 for schema dimension.
Descriptions are extremely brief (10-30 chars, e.g., 'Search the web for information'). Baseline for LLM-optimized descriptions is 50-200 chars. These lack context for when/why to use each tool, prerequisites, or what is returned. Per HARD SCORING RULES, descriptions under 20 chars cannot exceed 40 points.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 30 | 2026-07-28+ | v2 |
Fetch and parse website sitemaps
Search the web for information
No parameter descriptions visible for most tools. Even web_search and scrape show minimal descriptions ('Search query', 'URL to scrape'). LLMs cannot infer parameter meaning from names alone, a 'q' param needs context (free text? regex? max length?). Baseline: 100% of A+ tools have parameter descriptions.
No output schemas documented. LLMs cannot plan downstream tool calls or extract required fields without knowing what each tool returns. Baseline: 100% of A+ tools have documented return types.
No error handling guidance visible. Tools do not indicate what errors are retryable, user-fixable, or fatal. No recovery hints (e.g., 'If search fails, try a simpler query'). Agents cannot self-correct without actionable error messages.