All projects matching “extract”

Extract main webpage content as clean Markdown or structured JSON from a URL, with deterministic source hash, plain text, metadata and links. SSRF-safe with strict redirect and document-size limits.

Prompt-injection scan for text your AI agent is about to read (web pages, emails, tool output, MCP tool descriptions): risk score 0-100, verdict, categories and exact spans. Detects instruction overrides, jailbreak personas, system-prompt extraction, fake chat delimiters, data-exfiltration URLs, tool hijacking, hidden Unicode and encoded payloads. Deterministic rules, no data stored.

Query a World ID-verified human expert agent. Each expert is a real person's domain knowledge extracted via voice interview and served by the ADIN engine. Discover experts at /api/bazaar.

Shopify & DTC E-Commerce Store Competitive Intelligence (/v1/shopify-intel) — Extracts live product catalogs, pricing tiers, SKU variants, and stock availability from any Shopify or e-commerce storefront. (https://shopify-intel.agentdiet.dev/v1/shopify-intel)

E-Commerce & SaaS Product Catalog / Price Extractor (/v1/shopify-spy) — Extracts normalized product catalogs, live prices, variants, and availability from online stores. (https://shopify-spy.agentdiet.dev/v1/shopify-spy)

B2B Company, Tech Stack & Contact Lead Enrichment (/v1/company-enrich) — Extracts verified emails, social links, 40+ tech stack signals, pricing tiers, and company summary for GTM & research agents. (https://company-enrich.agentdiet.dev/v1/company-enrich)

SuperOracle: Extract to JSON

SEC-Intel EDGAR 10-K/10-Q Financial & Risk Extractor: Extracts structured financial metrics and risk factors from live SEC EDGAR filings.

Extract the current price, original price, currency, discount and availability from a public ecommerce, product or software pricing page.

Search the web with AI-oriented result extraction.

Extract named fields from unstructured text into strict JSON. Use when an agent must turn an email, filing, invoice, or description into {field: value} records up to 4,000 characters.

Grab this tool when a user wants a comprehensive news briefing with analysis. Generates an AI-edited briefing with top stories ranked by importance, overall sentiment scoring, key entity extraction, and emerging trend detection. Essential for staying informed efficiently.

Fetch a public web page and return clean LLM-ready Markdown (Readability main-content extraction, nav/scripts stripped) plus title, byline, excerpt and OpenGraph metadata. {fullPage:true} keeps the whole body; {maxChars} caps output (default 100k). No JS rendering.

Extract important application, submission, tender, grant, registration, and response deadlines from a public webpage.

Web content extraction: fetch any public URL and get clean readable text, title, meta description, OpenGraph data, headings, links and word count as JSON. Built for AI agents that need web page content without HTML noise.

Extract structured supplier, compliance, financial, experience, document and evaluation requirements from a public tender or procurement webpage.

Deterministic LLM red-team scan: prompt injection, jailbreak, system-prompt extraction and MCP tool abuse in agent prompts.

Fetches a web page server-side and returns a clean text extract with token-count estimates. Strips scripts, styles, navigation, ads and boilerplate. Served in JSON. $0.002 per call.

Structured-data extraction for a target URL.

Bulk web search — run up to 5 search queries in one paid call and get ranked results per query (title, URL, snippet, relevance score) as clean JSON. Same news, finance, date-range, country and domain filters as single web search, applied to every query. One payment instead of five for research fan-out, multi-query RAG retrieval and agent planning.

Use it before you send to an address, or to screen sign-ups and leads for typos, disposable domains and role addresses. Checks syntax, MX records (with the A-record fallback), null MX, a list of about 120,000 disposable domains, role addresses (info@, support@…) and free providers, without sending anything. No SMTP probing, so it can't confirm the mailbox exists. Never charged for errors: we settl

Fee inputs for the next transaction: gas ladder for Base or Ethereum (slow/normal/fast, priority fee, max fee, EIP-1559 base fee) or the priority-fee ladder for Solana, plus the native token price. One call for the numbers a transaction builder needs.

Base token check: send an ERC-20 contract address on Base and get verifiable on-chain facts as JSON (name, supply, owner and whether ownership is renounced, upgradeable proxy, verified source, privileged-function hints such as mint/pause/blacklist, WETH/USDC liquidity on Uniswap V2/V3 and Aerodrome) plus risk flags and a short plain-language summary. Facts only, not financial advice. Does not chec

Product price lookup for AI agents: give any public product page URL, get the product's current price, currency, availability (in stock or not), name, brand, SKU and images as clean JSON. The page is rendered in a real browser, so JavaScript stores work, and the store's own schema.org product data is read first. For price checks, price monitoring and comparing stores before you buy.

Firecrawl v2 API proxy — scrape. JSON body matches https://docs.firecrawl.dev/api-reference/v2-introduction. Poll GET routes are free; POST/PUT/DELETE are x402. $0.042 USDC per request. Agent search: scrape, markdown, firecrawl, web scrape, scrape-lite.

Fetch a URL and return clean, token-efficient markdown

Markdown only: fetch a public web page (robots.txt respected) and return clean Markdown plus title/word count. Cheaper than /v1/extract when you do not need structured product/table JSON.

Fetch one public static HTML page after robots and public-address checks, then return bounded readable text, title, final URL and source links. Standard x402: POST the URL, sign the 402 and resend the same body. The 402 also returns an encrypted payment_request that pays for exactly the quoted fetch. No browser, login, summary or full-site crawl.

Use when an agent has the text of a Japanese invoice or receipt (e.g. OCR output) and needs exact amounts without LLM misreads. Returns registration number (T+13, check digit only, not an NTA registry lookup), total, subtotal, 8%/10% tax breakdown and issue/due dates (Reiwa to ISO). Deterministic rules; text only, no images/PDF. Errors before payment (no charge): 400 body not {text} or over 5000 c

Give this API a web address and it will visit that page, then hand back everything an SEO professional needs to know: the page title, meta description, meta keywords, robots instructions, canonical link, H1/H2/H3 headings, how many links are on the page, and the HTTP status code. No setup required — just paste a URL and get structured data back in under two seconds.