Returns complete Web3 x402 micropayment configuration, supported multi-chain USDC contract addresses, EVM network chain IDs (Polygon: 137, Base: 8453, Arbitrum: 42161), recipient wallet address, and pricing tiers for all CleanWeb Studio agent tools.

Usage Guidelines:

• Use this tool to discover network parameters and deposit requirements before making x402 paid queries.

• Returns: Structured pricing markdown table, contract addresses, and pre-funded vault endpoints.

• Do NOT use for checking individual wallet balances (use get_vault_balance).

Scrapes and converts any target web page into clean, LLM-ready structured Markdown, stripping ads, cookie banners, navigation clutter, modals, and script noise.

Usage Guidelines:

• Use this tool to ingest real-time web articles, blogs, and documentation into LLM context windows.

• Returns: Clean markdown body, page title, word count, and extraction metadata.

• Do NOT use for YouTube video parsing (use clean_youtube_transcript).

• Do NOT use for PDF whitepapers or academic papers (use clean_pdf_research).

• Do NOT use for paywalled, login-required, or bot-blocked sites.

Extracts high-precision subtitles, timestamped transcripts, and comprehensive AI summaries for public YouTube videos using Google Gemini Flash intelligence.

Usage Guidelines:

• Use this tool to ingest YouTube lecture, tutorial, tech talk, or podcast transcripts into agent workflows.

• Returns: Video metadata (title, channel, URL), AI Knowledge Summary, and cleaned transcript.

• Do NOT use for general web pages or articles (use clean_web_content).

• Do NOT use for PDF documents or papers (use clean_pdf_research).

• Do NOT use for private, unlisted, age-restricted, or live streams without existing closed captions.

• If captions are missing or auto-captions fail, the tool reports a detailed fallback error.

Parses and extracts structured plain text, sections, and academic metadata from online PDF whitepapers and research papers.

Usage Guidelines:

• Use this tool to ingest scientific papers (e.g., arXiv), technical documentation, or financial reports.

• Constraint: Target document must be a direct HTTP/HTTPS URL pointing to a PDF file under 15MB.

• Returns: Title, total/parsed page count, word count, and extracted text.

• Do NOT use for general HTML web pages (use clean_web_content).

• Do NOT use for YouTube videos (use clean_youtube_transcript).

• Do NOT use for password-protected, DRM-encrypted, or scanned image-only PDFs without OCR.

Checks the remaining pre-funded USDC balance, total usage, and session status for an agent wallet address or session key.

Usage Guidelines:

• Use this tool before executing heavy tasks to verify sufficient balance for zero-latency execution.

• Returns: Agent address, available balance in USDC, total deposited, total consumed, queries handled, and session key.

• Do NOT use for querying pricing or chain parameters (use get_payment_info).

Executes real-time web search, noise-free markdown extraction, Gemini AI JSON structuring, and cryptographically signs the result with an on-chain verifiable EIP-712 attestation (0.035 USDC).

Usage Guidelines:

• Use this tool when an autonomous agent or smart contract requires verified, tamper-proof ground truth from the live web.

• Returns: Structured facts JSON, human/LLM readable summary markdown, source URLs, and EIP-712 cryptographic signature (v, r, s).

• Smart contracts can verify this off-chain or on-chain using CleanWebOracleVerifier.sol.

Verifies an EIP-712 cryptographic attestation produced by CleanWeb Oracle off-chain without consuming gas.

Usage Guidelines:

• Use this tool to mathematically verify that data received from CleanWeb Oracle has not been tampered with.

• Returns: Verification status (valid/invalid), recovered signer address, expected oracle address, and message.

Extracts pure, tag-free plain text optimized for RAG embedding and vector indexing (0.001 USDC).

Usage Guidelines:

• Use this tool when ingesting raw webpage text directly into vector databases (Pinecone, Chroma, Qdrant).

• Returns: Page title, word count, clean text, and token metrics.

Discovers domain sitemap or traverses internal anchor links to return a canonical URL tree (0.002 USDC).

Usage Guidelines:

• Use this tool to map an entire website or documentation site before scraping.

• Firecrawl /map equivalent for autonomous web navigation agents.

• Returns: Target URL, domain, total URL count, list of discovered URLs, and sitemap detection status.

Performs fast real-time keyword web search returning titles, links, and text snippets (0.002 USDC).

Usage Guidelines:

• Tavily / s.jina.ai competitor designed specifically for LLM autonomous agent retrieval.

• Returns: Concise search result list with title, verified URL, and text snippet.

Extracts schema-constrained structured JSON data from any webpage using Gemini AI (0.030 USDC).

Usage Guidelines:

• Use when an agent needs structured attributes (e.g. pricing, specs, event dates) directly from a URL.

• Returns: Clean JSON dictionary matching the requested schema description.

Performs multi-source web crawling and AI synthesis to generate an executive research briefing (0.150 USDC).

Usage Guidelines:

• Use when an agent needs a comprehensive deep dive into a topic with verified source citations.

• Returns: Full executive briefing markdown with source citations and key takeaways.

Concurrently scrapes and extracts clean markdown from up to 10 URLs in parallel with high-speed async processing (0.005 USDC).

Usage Guidelines:

• Use when an agent needs to perform multi-source research across multiple search results simultaneously.

• Returns: Formatted summary and content preview of parsed web documents.

Checks the active subscription status, remaining query quota, and validity period for an agent EVM wallet address (0x...) or Agent VIP Pass Token.

Usage Guidelines:

• Use to verify micropayment allowance or query entitlements before dispatching heavy scrape batches.

• Returns: Pass tier, remaining balance, and expiration timestamp.