superhighway-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| X402_NETWORK | No | Network to use for payments (base or base-sepolia) | base |
| AGENT_PRIVATE_KEY | Yes | Your funded Base wallet private key (0x...) to pay for web searches |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| web_searchA | Real-time web search. Returns ranked organic results (title, url, snippet) as JSON from a multi-engine metasearch. Paid per call in USDC via x402 — no signup, no API key. Use for fresh facts, research, fact-checking, and grounding/RAG. |
| news_searchA | Real-time news search. Returns recent news articles (title, url, snippet, published date) as JSON from a multi-engine news metasearch. Paid per call in USDC via x402 — no signup, no API key. Use for current events, breaking news, monitoring, and time-sensitive facts. |
| scrapeA | Read any web page as clean text + markdown. Give a URL, get back the page title, readable markdown, and plain text. Paid per call in USDC via x402 — no signup, no API key. Use to let the agent read pages, fetch articles/docs it can't access, scrape content, and feed RAG. |
| researchA | One-call web research: searches the live web AND reads the top result pages as clean markdown — content, not just links. Give a question, get ranked results plus the readable text of the best pages ($0.005/call in USDC via x402 — no signup, no API key). Use to answer questions from fresh sources in a single tool call instead of search-then-scrape round-trips. |
| image_searchA | Image search. Returns direct image URLs, source pages, and thumbnails as JSON from a multi-engine image metasearch. Paid per call in USDC via x402 — no signup, no API key. Use for visual grounding, finding images for content generation, and multimodal research. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool targets a distinct source or operation: images, news, web search, combined search+scrape, and raw scraping. The descriptions clearly differentiate their use cases, so an agent can easily select the right one.
Tool names mostly follow a verb_noun pattern (e.g., web_search, news_search, image_search), but 'scrape' is a bare verb and 'research' is a noun, creating a minor inconsistency. Overall still readable and predictable.
Five tools cover the essential web research functionality without redundancy or bloat. Each tool serves a clear purpose, and the count feels well-scoped for the stated domain.
The set covers image, news, and general web search, plus page scraping and a combined research operation. This spans the full typical workflow for web-based information retrieval, leaving no significant gaps.