# Context.dev

> ## Agent Instructions
> Setting up Context.dev for a user? Follow https://docs.context.dev/agent-quickstart.md. MCP clients sign in with OAuth and need no API key; application code reads CONTEXT_DEV_API_KEY.

- [Context.dev: the web data API](https://docs.context.dev/introduction.md): Fast web scraping with browsers, proxies, retries, batches, and monitors built in.
- [Quickstart](https://docs.context.dev/quickstart.md): Get an API key, install an SDK, scrape your first page, and check the response.
- [Agent quickstart](https://docs.context.dev/agent-quickstart.md): Instructions a coding agent follows to set up Context.dev: connect the MCP server to itself, add the API to application code, or install the CLI or skill.
- [SDKs](https://docs.context.dev/sdks.md): Install an official Context.dev SDK for TypeScript, Python, Ruby, Go, or PHP, and learn the key, timeout, and retry defaults they share.
- [JavaScript and TypeScript](https://docs.context.dev/sdks/typescript.md): Install the JavaScript and TypeScript SDK, scrape a page, look up a brand, and set timeouts and retries.
- [Python](https://docs.context.dev/sdks/python.md): Install the Python SDK, scrape a page, look up a brand, and set timeouts and retries.
- [Ruby](https://docs.context.dev/sdks/ruby.md): Install the Ruby SDK, scrape a page, look up a brand, and set timeouts and retries.
- [Go](https://docs.context.dev/sdks/go.md): Install the Go SDK, scrape a page, look up a brand, and set timeouts and retries.
- [PHP](https://docs.context.dev/sdks/php.md): Install the PHP SDK, scrape a page, look up a brand with the low-level request method, and set timeouts and retries.
- [MCP server](https://docs.context.dev/install-mcp.md): Connect Codex, Claude Code, Gemini CLI, Cursor, VS Code, or another MCP client to live Context.dev tools.
- [Agent skill](https://docs.context.dev/install-skill.md): Install the Context.dev skill so your coding agent picks the right endpoint, writes valid requests, and handles responses.
- [CLI](https://docs.context.dev/install-cli.md): Call Context.dev from your terminal with the context-dev CLI and use its JSON output in scripts and CI.
- [Scrape](https://docs.context.dev/scrape/overview.md): Get page content, images, structured data, and screenshots from one URL.
- [HTML](https://docs.context.dev/scrape/html.md): Return the page DOM after rendering and content filtering.
- [Markdown](https://docs.context.dev/scrape/markdown.md): Convert page content into Markdown for search, reading, or model context.
- [Screenshot](https://docs.context.dev/scrape/screenshot.md): Capture a viewport, full page, element, or rectangle as an inline image.
- [Images](https://docs.context.dev/scrape/images.md): Collect page image URLs and optionally add dimensions, classifications, and hosted files.
- [Bytes](https://docs.context.dev/scrape/bytes.md): Download the original response body as base64 with its content type.
- [Parse fields](https://docs.context.dev/scrape/parse-fields.md): Extract named fields with CSS selectors and deterministic rules.
- [Highlights](https://docs.context.dev/scrape/highlights.md): Return Markdown passages relevant to a question or topic.
- [JSON](https://docs.context.dev/scrape/json.md): Extract page facts into an object that follows your JSON Schema.
- [Product](https://docs.context.dev/scrape/product.md): Extract product details from a product page.
- [Browser actions](https://docs.context.dev/scrape/browser-actions.md): Interact with a page before capturing its outputs.
- [Waiting and rendering](https://docs.context.dev/scrape/waiting-and-rendering.md): Control page readiness, viewport size, theme, and popup handling.
- [Content filtering](https://docs.context.dev/scrape/content-filtering.md): Select the page regions used by text and image outputs.
- [Location and headers](https://docs.context.dev/scrape/location-and-headers.md): Choose a fetch country and send headers to the target site.
- [PDFs and documents](https://docs.context.dev/scrape/pdfs-and-documents.md): Extract text from a public document URL and optionally keep the original file.
- [Freshness and caching](https://docs.context.dev/scrape/freshness-and-caching.md): Choose when to reuse an output and when to fetch a fresh page.
- [Timeouts, limits, and errors](https://docs.context.dev/scrape/timeouts-and-errors.md): Handle deadlines, failed outputs, and response size limits.
- [YouTube videos](https://docs.context.dev/scrape/youtube.md): Read video metadata, descriptions, and available transcripts as Markdown.
- [Map URLs](https://docs.context.dev/map/overview.md): Discover a site’s URLs and available page metadata.
- [Filter and search](https://docs.context.dev/map/filter-and-search.md): Limit a URL inventory by path, subdomain, count, or topic.
- [Crawl](https://docs.context.dev/crawl/overview.md): Read a website’s pages as Markdown in one response.
- [Scope and limits](https://docs.context.dev/crawl/scope.md): Bound a crawl by page count, path, depth, and time.
- [Page content](https://docs.context.dev/crawl/page-content.md): Choose how each crawled page becomes Markdown.
- [Large crawls](https://docs.context.dev/crawl/async.md): Crawl a site in the background and retrieve Markdown or HTML when it finishes.
- [Search](https://docs.context.dev/search/overview.md): Find web pages from a query and optionally read each result’s content.
- [Filter results](https://docs.context.dev/search/filters.md): Narrow a web search by domain, recency, and location.
- [Result content](https://docs.context.dev/search/page-content.md): Read Markdown or highlights with search results and handle each page’s outcome.
- [Answers](https://docs.context.dev/answers/overview.md): Research a question and receive structured JSON with source URLs.
- [Answer shape](https://docs.context.dev/answers/answer-shape.md): Describe the answer using an example JSON object.
- [Sources and deadlines](https://docs.context.dev/answers/sources-and-deadlines.md): Use source URLs, partial answers, and research time limits correctly.
- [Parse documents](https://docs.context.dev/parse/overview.md): Upload file bytes and convert them into Markdown or HTML.
- [Supported formats](https://docs.context.dev/parse/formats.md): Choose file types and understand their Markdown output.
- [PDFs and OCR](https://docs.context.dev/parse/pdfs-and-ocr.md): Read scanned PDFs and images, with optional PDF page ranges.
- [Brand](https://docs.context.dev/brand/overview.md): Retrieve logos, colors, company details, and social links using one identifier.
- [Lookup by domain](https://docs.context.dev/brand/lookup-by-domain.md): Retrieve a profile for a known website domain.
- [Lookup by name](https://docs.context.dev/brand/lookup-by-name.md): Resolve a company name to its website and profile.
- [Lookup by email](https://docs.context.dev/brand/lookup-by-email.md): Resolve a work email’s domain to a company profile.
- [Lookup by ticker](https://docs.context.dev/brand/lookup-by-ticker.md): Resolve a stock ticker to a company profile.
- [Lookup by transaction](https://docs.context.dev/brand/lookup-by-transaction.md): Resolve a merchant descriptor with optional matching hints.
- [Lookup by page URL](https://docs.context.dev/brand/lookup-by-url.md): Extract brand details from one exact page.
- [Brand search](https://docs.context.dev/brand/search.md): Find up to ten brand candidates by company name or domain.
- [Styleguide](https://docs.context.dev/brand/styleguide.md): Extract colors, typography, spacing, and component styles from a website.
- [Logo Link](https://docs.context.dev/brand/logo-link.md): Embed a company logo using a public client ID and referring-domain restrictions.
- [Prefetch](https://docs.context.dev/brand/prefetching.md): Prepare brand or styleguide data before a later request.
- [People](https://docs.context.dev/people/overview.md): Find a person from identity clues and evaluate the returned match.
- [Enrich by email](https://docs.context.dev/people/enrich-by-email.md): Find a person from a work email, with optional company context.
- [Enrich by profile URL](https://docs.context.dev/people/enrich-by-profile-url.md): Use person-profile URLs as identity clues.
- [Enrich by name](https://docs.context.dev/people/enrich-by-name.md): Combine a full name with company, education, or location clues.
- [News](https://docs.context.dev/news/overview.md): Find articles about a company and page through the results.
- [Filter and sort](https://docs.context.dev/news/filter-and-sort.md): Select news by one source category, date window, and ordering.
- [Paginate news](https://docs.context.dev/news/paginate.md): Continue a news search using the returned cursor.
- [Industry classification](https://docs.context.dev/classification/eic.md): Read industry and subindustry labels from a Brand profile.
- [Batches](https://docs.context.dev/batches/overview.md): Scrape up to 25,000 URLs, or crawl a site, as one asynchronous job. Read each page's Markdown or HTML when the batch finishes.
- [Submit a batch](https://docs.context.dev/batches/submit.md): Submit URL lists with extraction options and safe retry keys.
- [Status and results](https://docs.context.dev/batches/results.md): Poll a batch until it finishes, read its records as paginated JSON or gzipped NDJSON files within 7 days, and find earlier batches.
- [Cancel, limits, and errors](https://docs.context.dev/batches/limits-and-errors.md): Cancel or delete a batch, stay within batch concurrency and rate limits, and handle each error the Batches API returns.
- [Monitors](https://docs.context.dev/monitors/overview.md): Watch a page, a sitemap, or a site's key pages on a schedule. Get changes by signed webhook or by polling runs and changes.
- [Monitor targets](https://docs.context.dev/monitors/targets.md): Configure page, sitemap, and extract targets, choose how changes are detected, and update a target without losing settings.
- [Monitor schedules](https://docs.context.dev/monitors/schedules.md): Set how often a monitor runs, run it on demand, pause and resume it, and learn when a monitor pauses itself.
- [Runs and changes](https://docs.context.dev/monitors/runs-and-changes.md): Read a monitor's changes and runs, including run statuses, error codes, and skip reasons, per monitor or across your account.
- [Monitor events and alerts](https://docs.context.dev/monitors/webhooks.md): Choose change.detected or run.completed events, turn on retries, track failing deliveries, and rotate a monitor's signing secret.
- [Limits and errors](https://docs.context.dev/monitors/limits-and-errors.md): Manage monitor allowances and handle state, validation, and access failures.
- [Webhooks](https://docs.context.dev/webhooks.md): Verify, retry, and replay batch and monitor events.
- [Credits and pricing](https://docs.context.dev/account/credits.md): Understand operation prices, request charges, and your organization’s credit balance.
- [Plans and billing](https://docs.context.dev/account/billing.md): Review plan limits, refills, plan changes, Auto-Topup, and cancellation.
- [API keys](https://docs.context.dev/account/api-keys.md): Create restricted credentials, inspect usage, and rotate access safely.
- [Team access](https://docs.context.dev/account/team.md): Manage organization roles, invitations, SSO, and offboarding.
- [Production checklist](https://docs.context.dev/optimization/best-practices.md): Prepare authentication, output handling, deadlines, and observability for production.
- [Timeouts](https://docs.context.dev/optimization/timeouts.md): Set an API deadline and keep client retries from multiplying unfinished work.
- [Rate limits](https://docs.context.dev/optimization/rate-limits.md): Pace requests by API key and use the separate organization limits for management APIs.
- [Troubleshooting](https://docs.context.dev/optimization/troubleshooting.md): Diagnose request errors, partial results, and empty data.
- [Usage and request logs](https://docs.context.dev/optimization/usage-and-logs.md): Label requests and investigate their metadata, input, and results.
- [Zero data retention](https://docs.context.dev/optimization/zero-data-retention.md): Bypass shared caches and keep request and response content out of retained logs.
- [Agent feedback](https://docs.context.dev/optimization/agent-feedback.md): Report an API issue or documentation mismatch with its request ID.
- [Responsible use](https://docs.context.dev/optimization/responsible-use.md): Understand the responsibilities that accompany third-party content and company data.
- [Security and API stability](https://docs.context.dev/optimization/trust.md): Find security evidence, data controls, service status, and API compatibility guidance.
- [Scrape Anything](https://docs.context.dev/api-reference/web-scraping/scrape.md): Scrape anything from a URL on the internet. Returns the outputs you enable in formats. Handles PDFs, DOCX, PPT, XLSX, and 40 other file formats.
- [Map URLs](https://docs.context.dev/api-reference/web-scraping/map.md): Discover a site's URLs, with page titles, descriptions, keywords, and language when available. Metadata can be missing on newly discovered URLs.
- [Crawl a website](https://docs.context.dev/api-reference/web-scraping/crawl.md): Crawl a website and return page content as Markdown. Use a batch for crawls beyond 500 pages.
- [Search the web](https://docs.context.dev/api-reference/web-scraping/search.md): Search the web and optionally return page content or relevant passages with each result.
- [Answer questions](https://docs.context.dev/api-reference/web-extraction/answers.md): Research the web and return a sourced answer in your JSON shape. Choose `fast` for a short task or `ultra` for deeper research.
- [Parse a file](https://docs.context.dev/api-reference/utility/parse.md): Convert uploaded file bytes into Markdown and optional HTML.
- [Retrieve a brand](https://docs.context.dev/api-reference/brand-intelligence/brand.md): Retrieve logos, colors, company details, and social links using one lookup identifier. A direct URL limits extraction to that page.
- [Search brands](https://docs.context.dev/api-reference/brand-intelligence/search.md): Find up to 10 brands by name or domain, ordered by popularity. Use the returned domain to retrieve a full brand profile.
- [Extract a styleguide](https://docs.context.dev/api-reference/brand-intelligence/styleguide.md): Extract colors, typography, spacing, and component styles from a website.
- [Prefetch brand data](https://docs.context.dev/api-reference/utility/prefetch.md): Queue brand or styleguide data so a later lookup can return sooner.
- [Enrich a person](https://docs.context.dev/api-reference/people/enrich.md): Find a person from identity clues and return their profile with a match score. Requires a paid plan; free or disposable email addresses return 422.
- [Search news](https://docs.context.dev/api-reference/news/search.md): Find company news by name, domain, ticker, or ISIN. Filter articles and continue through results with a cursor.
- [Submit a batch](https://docs.context.dev/api-reference/batches/submit.md): Scrape up to 25,000 URLs, or crawl a site, asynchronously. Poll the batch ID or receive a webhook when it finishes.
- [List batches](https://docs.context.dev/api-reference/batches/list.md): List your batches, newest first, with optional filters.
- [Retrieve a batch](https://docs.context.dev/api-reference/batches/retrieve.md): Get batch progress and result download links. Result files are deleted 7 days after the batch finishes.
- [List batch results](https://docs.context.dev/api-reference/batches/results.md): Page through a finished batch’s results as JSON. Results remain available for 7 days.
- [Cancel a batch](https://docs.context.dev/api-reference/batches/cancel.md): Stop a batch from starting new pages. Pages already in progress finish before the batch becomes cancelled.
- [Delete a batch](https://docs.context.dev/api-reference/batches/delete.md): Permanently delete a finished batch and its results. Its webhook deliveries can no longer be retried.
- [Receive batch.completed events](https://docs.context.dev/api-reference/batches/webhooks/completed.md): Receive the batch’s final status and result links.
- [Receive batch.failed events](https://docs.context.dev/api-reference/batches/webhooks/failed.md): Receive the batch’s final status and result links.
- [Receive batch.cancelled events](https://docs.context.dev/api-reference/batches/webhooks/cancelled.md): Receive the batch’s final status and result links.
- [Create a monitor](https://docs.context.dev/api-reference/monitors/create.md): Watch a page, URL inventory, or extracted website data on a schedule. A run starts immediately to capture the baseline.
- [List monitors](https://docs.context.dev/api-reference/monitors/list.md): List your monitors with optional search and filters.
- [Retrieve a monitor](https://docs.context.dev/api-reference/monitors/retrieve.md): Retrieve a monitor’s configuration and current state.
- [Update a monitor](https://docs.context.dev/api-reference/monitors/update.md): Update a monitor. Changing its target or change detection replaces the baseline and queues a new baseline run.
- [Delete a monitor](https://docs.context.dev/api-reference/monitors/delete.md): Delete a monitor and stop future runs and webhook retries.
- [Run a monitor now](https://docs.context.dev/api-reference/monitors/run.md): Queue a run without changing the regular schedule. Paused monitors return 409.
- [List monitor runs](https://docs.context.dev/api-reference/monitors/runs.md): List a monitor’s runs, newest first.
- [Retrieve a monitor run](https://docs.context.dev/api-reference/monitors/retrieve-run.md): Retrieve the status, timing, and results of one monitor run.
- [List runs for all monitors](https://docs.context.dev/api-reference/monitors/account-runs.md): List runs across your monitors, newest first.
- [List monitor changes](https://docs.context.dev/api-reference/monitors/changes.md): List full change records for a monitor, newest first.
- [Retrieve a monitor change](https://docs.context.dev/api-reference/monitors/change.md): Retrieve a detected change, including its diff and available evidence.
- [List changes for all monitors](https://docs.context.dev/api-reference/monitors/account-changes.md): List full change records across your monitors, newest first.
- [Retrieve monitor limits](https://docs.context.dev/api-reference/monitors/limits.md): Retrieve your organization’s monitor allowance and usage.
- [Retrieve monitor credit usage](https://docs.context.dev/api-reference/monitors/credit-usage.md): Return usage per monitor, highest first, for up to the 10,000 most recent runs in the requested window.
- [Receive change.detected events](https://docs.context.dev/api-reference/monitors/webhook-payload.md): Receive a signed monitor event.
- [Receive run.completed events](https://docs.context.dev/api-reference/monitors/webhook-run-completed.md): Receive a signed monitor event.
- [Rotate a monitor webhook secret](https://docs.context.dev/api-reference/monitors/rotate-webhook-secret.md): Generate and return a new signing secret. It takes effect immediately for all subsequent delivery attempts.
- [List webhook deliveries](https://docs.context.dev/api-reference/webhooks/list.md): List batch and monitor webhook deliveries from the last 30 days.
- [Retrieve a webhook delivery](https://docs.context.dev/api-reference/webhooks/retrieve.md): Retrieve a webhook delivery’s status and original payload.
- [List webhook delivery attempts](https://docs.context.dev/api-reference/webhooks/attempts.md): List a delivery’s attempts, newest first.
- [Retry a webhook delivery](https://docs.context.dev/api-reference/webhooks/retry.md): Resend the original payload using the source’s current URL and secret. Available for 7 days after the event.
- [List request logs](https://docs.context.dev/api-reference/logs/list.md): List your organization’s request logs with filters and pagination. Logs also include batch settlements and monitor runs.
- [Retrieve a request log](https://docs.context.dev/api-reference/logs/retrieve.md): Retrieve a request’s metadata, retained input, and response.
- [Submit agent feedback](https://docs.context.dev/api-reference/feedback/submit.md): Report an API issue or documentation mismatch, including request IDs when available.
- [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.
- [Website and PDF RAG](https://docs.context.dev/use-cases/build-rag-from-websites.md): Collect web pages and files into a searchable corpus with source identity and checked citations.
- [Datasets and comparisons](https://docs.context.dev/use-cases/structured-web-datasets.md): Collect structured web observations, preserve history, and compare verified facts.
- [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.
- [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.
- [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.
- [Enrich signups and leads](https://docs.context.dev/use-cases/lead-enrichment.md): Suggest company fields, enrich CRM records, and preserve user edits.
- [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.
- [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.
- [Branded content from brand context](https://docs.context.dev/use-cases/branded-documents.md): Reuse reviewed brand data across documents, websites, email, and campaign assets.
- [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.
- [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.
- [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.
- [Claude](https://docs.context.dev/integrations/claude-connector.md): Connect Claude to Context.dev for live web research and company data.
- [ChatGPT](https://docs.context.dev/integrations/chatgpt-plugin.md): Search the web, read pages, and retrieve company data from a ChatGPT conversation.
- [Cursor](https://docs.context.dev/integrations/cursor-plugin.md): Add Context.dev tools and API guidance to Cursor with the marketplace plugin.
- [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.
- [Replit](https://docs.context.dev/integrations/replit.md): Connect Replit Agent to Context.dev for live web research, scraping, and company data.
- [Smithery](https://docs.context.dev/integrations/smithery.md): Install Context.dev through Smithery or call its tools from the Smithery CLI.
- [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.
- [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, document parsing, and brand data.
- [Convex](https://docs.context.dev/integrations/convex.md): Scrape pages and retrieve company data from typed Convex actions.
- [Swytchcode](https://docs.context.dev/integrations/swytchcode.md): Call Context.dev from AI agents through Swytchcode's managed API execution layer.
- [Zapier](https://docs.context.dev/nocode/zapier.md): Enrich spreadsheet rows, research websites, and send change alerts with Context.dev in Zapier.
- [Make](https://docs.context.dev/nocode/make.md): Retrieve a company profile in Make and pass its fields to the next step.
- [Spreadsheets](https://docs.context.dev/nocode/spreadsheets.md): Display company logos in Google Sheets and Microsoft Excel with Logo Link.
- [Changelog](https://docs.context.dev/changelog.md): New features, improvements, and changes that affect your integration.

## OpenAPI Specs

- [openapi](/openapi.json)