# Context.dev

- [The go-to web data API](https://docs.context.dev/introduction.md): Scrape websites into Markdown, crawl linked pages, and extract JSON for AI agents and applications.
- [Human Quickstart](https://docs.context.dev/quickstart.md): Get an API key, make a request, and check the result.
- [Agent Quickstart](https://docs.context.dev/agent-quickstart.md): Give your agent one prompt to choose the right setup, connect Context.dev, and verify a first result.
- [JavaScript and TypeScript](https://docs.context.dev/sdks/typescript.md): Install the JavaScript and TypeScript SDK, scrape a webpage, and retrieve brand data.
- [Python](https://docs.context.dev/sdks/python.md): Install the Python SDK, scrape a webpage, and retrieve brand data.
- [Ruby](https://docs.context.dev/sdks/ruby.md): Install the Ruby SDK, scrape a webpage, and retrieve brand data.
- [Go](https://docs.context.dev/sdks/go.md): Install the Go v2 SDK, scrape a webpage, and retrieve brand data.
- [PHP](https://docs.context.dev/sdks/php.md): Install the PHP SDK, scrape a webpage, and retrieve brand data.
- [Connect MCP](https://docs.context.dev/install-mcp.md): Connect your AI client to Context.dev tools for live web and company data.
- [Skill](https://docs.context.dev/install-skill.md): Teach your coding agent how to choose and use the Context.dev API.
- [Install the CLI](https://docs.context.dev/install-cli.md): Call Context.dev from your terminal and use JSON responses in scripts or CI.
- [Scrape a webpage](https://docs.context.dev/guides/scrape-websites-to-markdown.md): Turn one webpage into clean Markdown or rendered HTML, then control freshness, page selection, and dynamic content.
- [Extract structured data](https://docs.context.dev/guides/extract-structured-data-from-websites.md): Crawl relevant pages and return an object that matches your JSON Schema, with controls for grounding, coverage, and freshness.
- [Crawl Sync](https://docs.context.dev/guides/crawl-website.md): Crawl a small website section and return page Markdown in one response, with a maximum of 500 pages.
- [Crawl Async](https://docs.context.dev/guides/crawl-website-async.md): Crawl up to 25,000 pages in a background batch, track progress, and retrieve Markdown or HTML when the job finishes.
- [Discover website URLs](https://docs.context.dev/guides/discover-website-urls.md): Read a website's public sitemaps and return a filtered URL list without rendering each page.
- [Extract page images](https://docs.context.dev/guides/extract-page-images.md): Return an image manifest from a webpage, with optional dimensions, hosted copies, visual classification, and deduplication.
- [Capture a screenshot](https://docs.context.dev/guides/take-webpage-screenshot.md): Render an exact URL or a resolved site page and return a viewport, full-page, or offset PNG capture.
- [Use browser actions](https://docs.context.dev/guides/browser-actions.md): Click, wait, or scroll before scraping or extracting a page, then check which interactions succeeded.
- [Parse PDFs and documents](https://docs.context.dev/guides/parse-documents.md): Convert PDFs, Office documents, spreadsheets, and other files into Markdown. Recover scanned PDF pages with optional OCR.
- [Extract product data](https://docs.context.dev/guides/extract-product-from-websites.md): Detect a product-detail page or discover a small product set, then return normalized product fields with explicit missing-data handling.
- [Retrieve brand data](https://docs.context.dev/guides/get-brand-data.md): Resolve a domain, company name, work email, stock ticker, transaction descriptor, or direct URL into a structured brand profile.
- [Retrieve brands by domain](https://docs.context.dev/guides/retrieve-brand-by-domain.md): Get logos, colors, and company details from a domain, with controls for speed and freshness.
- [Retrieve brands by name](https://docs.context.dev/guides/retrieve-brand-by-name.md): Find a brand from its company name and add a country hint to improve ambiguous matches.
- [Retrieve brands by email](https://docs.context.dev/guides/retrieve-brand-by-email.md): Resolve the company behind a work email and handle free, disposable, invalid, or unmatched addresses safely.
- [Retrieve brands by ticker](https://docs.context.dev/guides/retrieve-brand-by-ticker.md): Resolve a public company from a stock ticker and add an exchange hint when the symbol is ambiguous.
- [Extract brands from URLs](https://docs.context.dev/guides/retrieve-brand-by-direct-url.md): Extract brand fields from one exact webpage without domain resolution, database lookup, or cross-source enrichment.
- [Extract a design system](https://docs.context.dev/guides/extract-design-system-from-website.md): Observe a page's colors, typography, spacing, shadows, buttons, and font assets as structured data.
- [Display a company logo](https://docs.context.dev/guides/get-logo-from-url.md): Embed a hosted company logo when one is available, with domain restrictions, fallbacks, and correct usage boundaries.
- [Enrich transaction descriptors](https://docs.context.dev/guides/enrich-transaction-codes.md): Resolve a card or bank-statement descriptor into a brand profile, with context that reduces ambiguous merchant matches.
- [Choose a classification system](https://docs.context.dev/guides/classification/overview.md): Choose EIC, NAICS, or SIC based on the system your product needs to interoperate with.
- [Read EIC industry labels](https://docs.context.dev/guides/classification/EIC.md): Read Context.dev's industry and subindustry labels from a Brand profile and handle missing or multiple classifications.
- [Retrieve NAICS industry codes](https://docs.context.dev/guides/classification/NAICS.md): Return 2022 NAICS codes from a domain or company name and decide how to use confidence in your workflow.
- [Retrieve SIC industry codes](https://docs.context.dev/guides/classification/SIC.md): Return four-digit SIC candidates from the 1987 classification or the current SEC-published list.
- [Scrape in batches](https://docs.context.dev/guides/scrape-websites-in-batches.md): Submit up to 25,000 URLs or crawl a site asynchronously, track progress, and consume results as paginated JSON or gzipped NDJSON.
- [Monitor website changes](https://docs.context.dev/guides/monitor-website-changes.md): Watch a page, sitemap, or structured dataset on a schedule and receive signed change events.
- [Production checklist](https://docs.context.dev/optimization/best-practices.md): Prepare your integration for missing data, slow requests, retries, and usage limits.
- [Troubleshooting](https://docs.context.dev/optimization/troubleshooting.md): Find the cause of an API error and decide whether to fix, retry, or skip the request.
- [Rate limits](https://docs.context.dev/optimization/rate-limits.md): Pace API requests and recover from 429 responses with bounded retries.
- [Responsible use](https://docs.context.dev/optimization/fair-use.md): Understand the rights, privacy, and product responsibilities that remain with you when using third-party web and brand data.
- [Prefetching](https://docs.context.dev/optimization/prefetching.md): Start a company or styleguide lookup before your application needs the result.
- [Response compression](https://docs.context.dev/optimization/compression.md): Use gzip to reduce the size of large scraping and crawl responses.
- [Request tags](https://docs.context.dev/optimization/tag-requests.md): Track API usage by environment, team, customer, or feature.
- [Zero data retention](https://docs.context.dev/optimization/zero-data-retention.md): Bypass shared caches and keep request and response content out of retained usage logs.
- [API stability](https://docs.context.dev/optimization/api-stability.md): Understand API versions, compatible changes, and SDK upgrades.
- [Security and trust](https://docs.context.dev/optimization/trust.md): Find security reports, data controls, service status, and procurement information.
- [Scrape Markdown](https://docs.context.dev/api-reference/web-scraping/markdown.md): Convert any page into clean Markdown optimized for agents, RAG, search, and analysis.
- [Scrape HTML](https://docs.context.dev/api-reference/web-scraping/html.md): Fetch raw page HTML for extraction, archiving, QA, and custom parsing workflows.
- [Scrape Images](https://docs.context.dev/api-reference/web-scraping/images.md): Find the images on any page and enrich them with metadata for brand, catalog, and content workflows.
- [Capture Screenshot](https://docs.context.dev/api-reference/web-scraping/screenshot.md): Capture production-ready website screenshots for previews, audits, brand libraries, and visual QA.
- [Crawl Sitemap](https://docs.context.dev/api-reference/web-scraping/sitemap.md): Discover every URL in a sitemap so your crawler, index, or enrichment job starts with complete coverage.
- [Crawl Website Content](https://docs.context.dev/api-reference/web-scraping/crawl.md): Crawl a website and return clean, LLM-ready Markdown pages that are ready to use in RAG pipelines, search indexes, and other content workflows.
- [Search the Web](https://docs.context.dev/api-reference/web-scraping/search.md): Search the web and optionally scrape results in one call so your product gets answers faster.
- [Extract Structured Data](https://docs.context.dev/api-reference/web-extraction/extract.md): Crawl a website and return schema-shaped data you can drop directly into products, agents, and workflows.
- [Parse File Bytes to Markdown](https://docs.context.dev/api-reference/utility/parse.md): Converts raw text, source code, web/data, PDF, Microsoft Office, and image bytes into LLM-usable Markdown.
- [Submit a Batch](https://docs.context.dev/api-reference/batches/submit.md): Scrape 25K URLs or crawl large websites asynchronously.
- [List Batches](https://docs.context.dev/api-reference/batches/list.md): List your batches from newest to oldest. Filter by status or continue with a cursor.
- [Retrieve a Batch](https://docs.context.dev/api-reference/batches/retrieve.md): Check progress, and get download links once the batch finishes.
- [List Batch Results](https://docs.context.dev/api-reference/batches/results.md): Page through a finished batch's results as JSON instead of downloading the NDJSON files.
- [Cancel a Batch](https://docs.context.dev/api-reference/batches/cancel.md): Stop a batch from starting new pages. In-progress pages finish, and unused credits are refunded.
- [Delete a Batch](https://docs.context.dev/api-reference/batches/delete.md): Permanently delete a finished batch and its stored results. Active batches must settle first.
- [Receive batch.completed webhooks](https://docs.context.dev/api-reference/batches/webhooks/completed.md): Sent when a batch completes. Return any 2xx response to acknowledge delivery.
- [Receive batch.failed webhooks](https://docs.context.dev/api-reference/batches/webhooks/failed.md): Sent when a batch fails. Return any 2xx response to acknowledge delivery.
- [Receive batch.cancelled webhooks](https://docs.context.dev/api-reference/batches/webhooks/cancelled.md): Sent when a batch is cancelled. Return any 2xx response to acknowledge delivery.
- [Retrieve Brand Data](https://docs.context.dev/api-reference/brand-intelligence/brand.md): Enrich signups, CRM records, and transactions with logos, colors, descriptions, socials, and industry data.
- [Search Brands](https://docs.context.dev/api-reference/brand-intelligence/search.md): Search indexed brands by name or domain and return up to 10 lightweight prefix matches for autocomplete.
- [Extract Styleguide](https://docs.context.dev/api-reference/brand-intelligence/styleguide.md): Extract colors, typography, spacing, shadows, and UI cues from any site to build on-brand experiences faster.
- [Scrape Fonts](https://docs.context.dev/api-reference/brand-intelligence/fonts.md): Detect the fonts a site uses so your app can match brand typography without manual inspection.
- [Prefetch Brand Data](https://docs.context.dev/api-reference/utility/prefetch.md): Warm the brand cache before users need it so onboarding and enrichment flows return faster.
- [Enrich Person](https://docs.context.dev/api-reference/people/enrich.md): Enrich a person from combined identity clues and receive an identity match score.
- [Search Company News](https://docs.context.dev/api-reference/news/search.md): Search live and historical company news by name, domain, ticker, or ISIN.
- [Extract Product Data](https://docs.context.dev/api-reference/web-extraction/product.md): Turn a product page into structured pricing, features, imagery, and metadata your app can use immediately.
- [Extract Products](https://docs.context.dev/api-reference/web-extraction/products.md): Build a structured product catalog from any brand website — names, prices, images, and descriptions — without writing custom scrapers.
- [Classify NAICS Industries](https://docs.context.dev/api-reference/web-extraction/naics.md): Map any brand to NAICS industry codes for cleaner segmentation, routing, and analytics.
- [Classify SIC Industries](https://docs.context.dev/api-reference/web-extraction/sic.md): Map brands to SIC codes for finance, compliance, segmentation, and industry analysis.
- [Create a Monitor](https://docs.context.dev/api-reference/monitors/create.md): Creates a monitor. The request body is a union of the supported target/change detection combinations. The monitor runs immediately after creation to create its initial baseline.
- [List Monitors](https://docs.context.dev/api-reference/monitors/list.md): List your organization's monitors with free-text search plus status, target type, and tag filters.
- [Retrieve a Monitor](https://docs.context.dev/api-reference/monitors/retrieve.md): Fetch a monitor's full configuration, status, schedule, and current baseline by ID.
- [Update a Monitor](https://docs.context.dev/api-reference/monitors/update.md): Updates a monitor. If `target` or `change_detection` changes, the monitor creates a new baseline. Unsupported target/change detection combinations are rejected.
- [Delete a Monitor](https://docs.context.dev/api-reference/monitors/delete.md): Permanently remove a monitor and stop all of its scheduled runs.
- [Retrieve Monitor Limits](https://docs.context.dev/api-reference/monitors/limits.md): Returns how many monitors the account has and the maximum it allows.
- [Retrieve Monitor Credit Usage](https://docs.context.dev/api-reference/monitors/credit-usage.md): See credits charged per monitor over a time window so you always know what your monitors cost.
- [Run a Monitor Now](https://docs.context.dev/api-reference/monitors/run.md): Queue an immediate run outside the monitor's normal schedule. The run is processed asynchronously.
- [List Monitor Runs](https://docs.context.dev/api-reference/monitors/runs.md): List a monitor's run history with status, timing, credits charged, and any detected change per run.
- [Retrieve a Monitor Run](https://docs.context.dev/api-reference/monitors/retrieve-run.md): Fetch a single run by id, including its lifecycle status, timing, credits charged, and any change detected.
- [List Account Runs](https://docs.context.dev/api-reference/monitors/account-runs.md): Get an account-wide feed of monitor runs across all monitors in your organization.
- [List Monitor Changes](https://docs.context.dev/api-reference/monitors/changes.md): List the changes a monitor has detected, filterable by time window and tag.
- [Retrieve a Change](https://docs.context.dev/api-reference/monitors/change.md): Fetch full change details: text diffs, added and removed URLs, semantic evidence, confidence, and importance.
- [List Account Changes](https://docs.context.dev/api-reference/monitors/account-changes.md): Get an account-wide feed of detected changes across all monitors, filterable by monitor, type, time, and tag.
- [Receive change.detected webhooks](https://docs.context.dev/api-reference/monitors/webhook-payload.md): Sent when a monitor detects a change. Return any 2xx response to acknowledge delivery.
- [Receive run.completed webhooks](https://docs.context.dev/api-reference/monitors/webhook-run-completed.md): Sent after each completed monitor run, including runs with no changes. Return any 2xx response to acknowledge delivery.
- [Rotate a Monitor Webhook Secret](https://docs.context.dev/api-reference/monitors/rotate-webhook-secret.md): Generate a new signing secret for a monitor's webhook. The previous secret stops signing deliveries immediately.
- [List Webhook Deliveries](https://docs.context.dev/api-reference/webhooks/list.md): List your batch or monitor webhook deliveries, newest first.
- [Retrieve a Webhook Delivery](https://docs.context.dev/api-reference/webhooks/retrieve.md): Get a webhook delivery, including its status and latest attempt.
- [List Webhook Delivery Attempts](https://docs.context.dev/api-reference/webhooks/attempts.md): List delivery attempts, newest first.
- [Retry a Webhook Delivery](https://docs.context.dev/api-reference/webhooks/retry.md): Retry a webhook delivery within seven days of creation.
- [List Request Logs](https://docs.context.dev/api-reference/logs/list.md): List your organization's API requests, newest first. Defaults to the last 24 hours.
- [Retrieve a Request Log](https://docs.context.dev/api-reference/logs/retrieve.md): Get one logged API call, including its request input and response body.
- [Prefill and personalize onboarding](https://docs.context.dev/use-cases/faster-onboarding-flows.md): Turn a business email into editable company fields and a workspace theme without blocking signup or replacing user choices.
- [Build a company directory with logos](https://docs.context.dev/use-cases/company-directory-logos.md): Add recognizable company logos to directories, job boards, and account lists, with fallbacks and persistent corrections.
- [Build a recognizable merchant feed](https://docs.context.dev/use-cases/merchant-transaction-feeds.md): Turn merchant domains or transaction descriptors into readable transaction rows while preserving unresolved states and user corrections.
- [Generate a website from brand context](https://docs.context.dev/use-cases/generate-branded-websites.md): Turn observed company branding into a small website theme, approved page content, and an editable responsive preview.
- [Enrich companies and contacts](https://docs.context.dev/use-cases/lead-enrichment.md): Fill missing company fields, add person context and sourced account research, and preserve your team's CRM edits.
- [Create a personalized sales demo](https://docs.context.dev/use-cases/personalized-sales-demos.md): Use a prospect's domain to prepare a branded demo with sourced account facts, editable content, and a reviewable sharing step.
- [Generate branded decks, proposals, and reports](https://docs.context.dev/use-cases/branded-documents.md): Map company branding into a reviewed document theme, render approved content, and preserve the source version with each export.
- [Generate campaign assets](https://docs.context.dev/use-cases/branded-campaign-assets.md): Use company logos, design tokens, and website copy to create a reusable campaign brief.
- [Build branded emails](https://docs.context.dev/use-cases/custom-email-templates.md): Turn a company's logo, colors, and website imagery into an email brief and tested HTML template.
- [Give an AI agent live web context](https://docs.context.dev/use-cases/live-web-context-for-agents.md): Build bounded search and read tools that return sourced Markdown, expose failed reads, and keep citations tied to retrieved evidence.
- [Build RAG from websites](https://docs.context.dev/use-cases/build-rag-from-websites.md): Crawl website content into Markdown, index it with source URLs, and build answers that cite those sources.
- [Build a refreshable dataset from websites](https://docs.context.dev/use-cases/structured-web-datasets.md): Discover source pages, extract nullable records, and update a durable dataset without duplicating rows or erasing good data after failures.
- [Research papers and PDFs with citations](https://docs.context.dev/use-cases/research-with-pdfs.md): Turn selected documents into retrievable evidence, preserve source metadata, and verify generated citations against the text you obtained.
- [Build a sourced competitor comparison](https://docs.context.dev/use-cases/competitor-research.md): Collect comparable product and pricing facts, retain sources and observation times, and keep interpretation separate from evidence.
- [Turn website changes into a useful digest](https://docs.context.dev/use-cases/website-change-digests.md): Monitor a reviewed watchlist, deduplicate signed events, and build a source-linked digest that also exposes failed checks.
- [Cursor](https://docs.context.dev/integrations/cursor-plugin.md): Add Context.dev tools and API guidance to Cursor with the marketplace plugin.
- [ChatGPT](https://docs.context.dev/integrations/chatgpt-plugin.md): Search the web, read pages, and retrieve company data from a ChatGPT conversation.
- [Claude](https://docs.context.dev/integrations/claude-connector.md): Connect Claude to Context.dev for live web research and company data.
- [Gemini CLI](https://docs.context.dev/integrations/gemini-cli.md): Add Context.dev live web and document intelligence to Gemini CLI with the official extension.
- [LangChain](https://docs.context.dev/integrations/langchain.md): Use Context.dev as native LangChain tools for live web data, documents, brand intelligence, monitors, and batches.
- [Composio](https://docs.context.dev/integrations/composio.md): Connect Context.dev to your agent framework through Composio for web scraping, structured extraction, and brand data.
- [Replit](https://docs.context.dev/integrations/replit.md): Connect Replit Agent to Context.dev for live web research, scraping, and company data.
- [Eve](https://docs.context.dev/integrations/eve.md): Give an Eve agent Context.dev tools with a separate connection for each user.
- [OpenClaw](https://docs.context.dev/integrations/openclaw.md): Add web search and scraping to OpenClaw, or connect the full Context.dev MCP server.
- [Smithery](https://docs.context.dev/integrations/smithery.md): Install Context.dev through Smithery or call its tools from the Smithery CLI.
- [Convex](https://docs.context.dev/integrations/convex.md): Scrape pages and retrieve company data from typed Convex actions.
- [Make](https://docs.context.dev/nocode/make.md): Retrieve a company profile in Make and pass its fields to the next step.
- [Zapier](https://docs.context.dev/nocode/zapier.md): Enrich spreadsheet rows, research websites, and send change alerts with Context.dev in Zapier.
- [Google Sheets](https://docs.context.dev/nocode/google-sheets.md): Display company logos in Google Sheets with Logo Link and the IMAGE() formula.
- [Microsoft Excel](https://docs.context.dev/nocode/microsoft-excel.md): Display company logos in Excel with Logo Link and the IMAGE() function.
- [Changelog](https://docs.context.dev/changelog.md): Month-by-month log of new Context.dev API endpoints, parameters, SDK releases, pricing updates, integrations, and other product changes.

## OpenAPI Specs

- [openapi](/openapi.json)