Skip to main content
Context.dev logo
  • Category: web scraping & browser
  • Auth: API_KEY
  • Composio-managed OAuth available? N/A
  • Tools: 13
  • Triggers: 0
  • Slug: CONTEXT_DEV
  • Version: 20261101_00
  • Instant: Supported on the latest version. Support varies by tool.

Tools

Slug: CONTEXT_DEV_EXTRACT_STRUCTURED_WEB_DATACrawl relevant pages from a website and return data matching a caller-provided JSON Schema and extraction instructions. This is a higher-cost metered call; use SCRAPE_WEBPAGE_MARKDOWN when Markdown is sufficient. The price increases with pages analyzed.Instant: Supported on the latest version.Instant pricing: From $0.025 per extraction; more pages cost more.Discount: 80

Input Parameters

string
required
Starting HTTP or HTTPS website URL to crawl.
array
Usage-tracking tags. Provide at most 20 tags of 1-50 characters each.
integer
Maximum link depth from the starting URL. Use 0 to analyze only the starting page; omit for no crawl-depth limit.
integer
Maximum pages to analyze (1-50). Higher values increase the price.
boolean
Require every returned value to be grounded in page content. Unsupported fields are returned as null or empty instead of inferred.
string
Optional extraction guidance or field interpretation, up to 2000 characters.
object
required
JSON Schema describing the object to extract. Add descriptions to non-obvious properties so the extractor can interpret them correctly.
integer
Soft crawl time budget in milliseconds (10000-110000).
boolean
Follow links on subdomains of the starting domain.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: CONTEXT_DEV_GET_BRANDRetrieve enriched brand identity, logos, colors, industry, and description using exactly one domain, name, work email, ticker, direct URL, or transaction descriptor. Use SEARCH_BRANDS for inexpensive discovery; this full enrichment costs more.Instant: Supported on the latest version.Instant pricing: $0.025 per brand retrievalDiscount: 80

Input Parameters

string
City hint for transaction lookup.
array
Up to 20 usage-tracking tags, each 1-50 characters.
string
Phone-number hint for transaction lookup, as text or a number.
string
Country hint for name or transaction lookup.
boolean
Prefer faster but potentially less comprehensive retrieval.
string
required
Domain, company name, work email, ticker, full direct URL, or transaction descriptor matching lookup_type.
integer
Maximum cached brand-data age in milliseconds. The provider clamps values to 1 day through 1 year.
integer
Provider timeout in milliseconds, from 1000 through 300000.
string ("domain" | "name" | "email" | "ticker" | "direct_url" | "transaction")
required
Kind of identifier supplied in identifier. Selects domain, company name, work email, stock ticker, direct URL, or transaction lookup.
string ("afrikaans" | "albanian" | "amharic" | "arabic" | "armenian" | "assamese" | "aymara" | "azeri" | "basque" | "belarusian" | "bengali" | "bosnian" | "bulgarian" | "burmese" | "cantonese" | "catalan" | "cebuano" | "chinese" | "corsican" | "croatian" | "czech" | "danish" | "dutch" | "english" | "esperanto" | "estonian" | "farsi" | "fijian" | "finnish" | "french" | "galician" | "georgian" | "german" | "greek" | "guarani" | "gujarati" | "haitian-creole" | "hausa" | "hawaiian" | "hebrew" | "hindi" | "hmong" | "hungarian" | "icelandic" | "igbo" | "indonesian" | "irish" | "italian" | "japanese" | "javanese" | "kannada" | "kazakh" | "khmer" | "kinyarwanda" | "korean" | "kurdish" | "kyrgyz" | "lao" | "latin" | "latvian" | "lingala" | "lithuanian" | "luxembourgish" | "macedonian" | "malagasy" | "malay" | "malayalam" | "maltese" | "maori" | "marathi" | "mongolian" | "nepali" | "norwegian" | "odia" | "oromo" | "pashto" | "pidgin" | "polish" | "portuguese" | "punjabi" | "quechua" | "romanian" | "russian" | "samoan" | "scottish-gaelic" | "serbian" | "sesotho" | "shona" | "sindhi" | "sinhala" | "slovak" | "slovene" | "somali" | "spanish" | "sundanese" | "swahili" | "swedish" | "tagalog" | "tajik" | "tamil" | "tatar" | "telugu" | "thai" | "tibetan" | "tigrinya" | "tongan" | "tswana" | "turkish" | "turkmen" | "ukrainian" | "urdu" | "uyghur" | "uzbek" | "vietnamese" | "welsh" | "wolof" | "xhosa" | "yiddish" | "yoruba" | "zulu")
Provider-supported output language name, such as english or french.
string
Stock exchange identifier for ticker lookup; omit to let Context.dev default to NASDAQ.
boolean
For transaction lookup, require additional match verification.
string
Merchant Category Code hint for transaction lookup, as text or a number.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: CONTEXT_DEV_GET_MONITOR_LIMITSReturn the connected account’s plan and current monitor usage versus its monitor limit.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: CONTEXT_DEV_GET_WEBDB_USAGEReturn WebDB credit balance, period consumption, row count, storage, and per-collection usage for an optional time range.

Input Parameters

array
Up to 20 usage-tracking tags, each 1-50 characters.
string
Inclusive end of the usage period as an ISO 8601 timestamp.
string
Inclusive start of the usage period as an ISO 8601 timestamp.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: CONTEXT_DEV_GET_WEBSITE_STYLEGUIDEExtract a website’s colors, typography, spacing, shadows, font assets, and common component styles from either a domain or one direct URL.Instant: Supported on the latest version.Instant pricing: $0.025 per website styleguide extractionDiscount: 80

Input Parameters

array
Usage-tracking tags. Supply at most 20 tags of 1-50 characters each.
string
Domain to resolve and inspect, such as example.com. Required when direct_url is omitted; do not supply both fields.
string
Exact HTTP or HTTPS page to inspect without domain resolution. Required when domain is omitted; do not supply both fields.
integer
Maximum cached-data age in milliseconds. The provider clamps values to between one day and one year.
integer
Provider request timeout in milliseconds, from 1000 through 300000.
string ("light" | "dark")
Browser color scheme to emulate for the extraction.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: CONTEXT_DEV_LIST_BATCHESList and filter the connected account’s asynchronous web batches from newest to oldest, returning one cursor-controlled page.

Input Parameters

array
Filter to batches having any of these tags; supply 1-20 tags.
integer
Maximum batches in this page, from 1 through 100.
string
Search batch ID, source URL or domain, and tags; maximum 200 characters.
string
Opaque next_cursor returned by a previous call; omit for the first page.
string ("queued" | "running" | "cancelling" | "completed" | "cancelled" | "failed")
Filter batches by lifecycle status.
string ("prefix" | "exact")
Use prefix matching for autocomplete or exact matching for full tokens.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: CONTEXT_DEV_LIST_MONITORSList and filter the connected organization’s web monitors, returning one cursor-controlled page.

Input Parameters

array
Filter to monitors having any of these tags; maximum 20 tags.
integer
Maximum monitors to return in this page, from 1 to 100.
string
Free-text term matched against search_fields, up to 200 characters.
string
Opaque next_cursor returned by a previous call; omit for the first page.
string ("active" | "paused" | "failed")
Filter by monitor lifecycle status.
string ("prefix" | "exact")
Use prefix matching for autocomplete or exact matching for full tokens.
string ("page" | "sitemap" | "extract")
Filter by monitor target type.
array
Monitor fields searched by query; omit to search all supported fields. Instructions exist only on extract monitors.
string ("exact" | "semantic")
Filter by change-detection strategy.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: CONTEXT_DEV_LIST_WEBDB_COLLECTIONSList the connected account’s WebDB collections and return one cursor-controlled page, including each collection’s sources, extraction configuration, status, usage, and timestamps.

Input Parameters

array
Up to 20 usage-tracking tags, each 1-50 characters. Context.dev records these tags with this list request.
integer
Maximum collections in this page, from 1 through 100.
string
Opaque next_cursor returned by a previous call; omit for the first page.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: CONTEXT_DEV_PARSE_FILEConvert an uploaded document, image, source file, or data file into LLM-usable Markdown.Instant: Supported on the latest version.Instant pricing: From $0.002 per non-OCR file parseDiscount: 80

Input Parameters

boolean
Whether to OCR selected PDF pages that lack usable text. Each page recovered with OCR adds to the price.
object
required
File to parse. Its raw contents must not exceed 25 MiB.
array
Usage-tracking tags. Provide at most 20 tags of 1 to 50 characters each.
integer
Last 1-based PDF page to parse. Must be at least pdf_start when both are set.
string ("txt" | "text" | "md" | "markdown" | "html" | "htm" | "xhtml" | "xml" | "rss" | "atom" | "csv" | "tsv" | "yaml" | "yml" | "py" | "java" | "js" | "jsx" | "mjs" | "cjs" | "json" | "jsonl" | "ndjson" | "php" | "sh" | "bash" | "zsh" | "fish" | "rb" | "ts" | "tsx" | "rtf" | "srt" | "css" | "scss" | "less" | "styl" | "sass" | "svg" | "pdf" | "docx" | "doc" | "xlsx" | "xlsm" | "xlsb" | "xltx" | "xltm" | "xls" | "pptx" | "pptm" | "ppsx" | "ppsm" | "potx" | "potm" | "ppt" | "pps" | "pot" | "jpg" | "jpeg" | "jpe" | "png" | "gif" | "bmp" | "tiff" | "tif" | "webp" | "ppm" | "pbm" | "pgm" | "pnm")
File-extension hint used when the format cannot be detected reliably.
integer
First 1-based PDF page to parse. Omit to start at the first page.
Whether to preserve hyperlinks in the Markdown output.
boolean
Whether to include image references in the Markdown output.
boolean
Whether to request zero-data-retention processing. The request fails if this feature is not enabled for the organization.
boolean
For HTML-like files, whether to omit navigation and other non-main content.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: CONTEXT_DEV_SCRAPE_WEBPAGE_MARKDOWNRender one public URL and return its content as Markdown, optionally restricting it to main content or CSS-selected regions. This free-tier tool does not perform paid browser actions.Instant: Supported on the latest version.Instant pricing: From $0.002 per Markdown webpage scrapeDiscount: 80

Input Parameters

string
required
Full HTTP or HTTPS URL to render and convert to Markdown.
array
Up to 20 usage-tracking tags, each 1-50 characters.
string ("ad" | "ae" | "af" | "ag" | "ai" | "al" | "am" | "ao" | "ar" | "at" | "au" | "aw" | "az" | "ba" | "bb" | "bd" | "be" | "bf" | "bg" | "bh" | "bi" | "bj" | "bm" | "bn" | "bo" | "bq" | "br" | "bs" | "bw" | "by" | "bz" | "ca" | "cd" | "cf" | "cg" | "ch" | "ci" | "cl" | "cm" | "cn" | "co" | "cr" | "cv" | "cw" | "cy" | "cz" | "de" | "dj" | "dk" | "dm" | "do" | "dz" | "ec" | "ee" | "eg" | "es" | "et" | "fi" | "fj" | "fr" | "ga" | "gb" | "gd" | "ge" | "gf" | "gg" | "gh" | "gm" | "gn" | "gp" | "gq" | "gr" | "gt" | "gu" | "gw" | "gy" | "hk" | "hn" | "hr" | "ht" | "hu" | "id" | "ie" | "il" | "im" | "in" | "iq" | "ir" | "is" | "it" | "je" | "jm" | "jo" | "jp" | "ke" | "kg" | "kh" | "kn" | "kr" | "kw" | "ky" | "kz" | "la" | "lb" | "lc" | "lk" | "lr" | "ls" | "lt" | "lu" | "lv" | "ly" | "ma" | "mc" | "md" | "me" | "mf" | "mg" | "mk" | "ml" | "mm" | "mn" | "mo" | "mq" | "mr" | "mt" | "mu" | "mv" | "mw" | "mx" | "my" | "mz" | "na" | "nc" | "ne" | "ng" | "ni" | "nl" | "no" | "np" | "nz" | "om" | "pa" | "pe" | "pf" | "pg" | "ph" | "pk" | "pl" | "pr" | "ps" | "pt" | "py" | "qa" | "re" | "ro" | "rs" | "ru" | "rw" | "sa" | "sc" | "sd" | "se" | "sg" | "si" | "sk" | "sl" | "sm" | "sn" | "so" | "sr" | "ss" | "st" | "sv" | "sx" | "sy" | "sz" | "tc" | "td" | "tg" | "th" | "tj" | "tl" | "tm" | "tn" | "tr" | "tt" | "tw" | "tz" | "ua" | "ug" | "us" | "uy" | "uz" | "vc" | "ve" | "vg" | "vi" | "vn" | "ye" | "yt" | "za" | "zm" | "zw")
Lowercase ISO 3166-1 alpha-2 country code for the residential proxy. Must be one of the provider-supported values.
integer
Maximum cached-result age in milliseconds, from 0 to 2592000000. Set 0 to force a fresh scrape.
integer
Provider-side request timeout in milliseconds, from 1 to 300000.
integer
Wait 0-30000 milliseconds after page load before capturing content.
Preserve hyperlinks in the Markdown output.
boolean
Include rendered iframe content in the Markdown output.
boolean
Include image references in the Markdown output.
array
Remove content matching these CSS selectors after inclusion filtering; maximum 50.
array
Keep only content matching these CSS selectors; maximum 50.
boolean
Wait briefly for CSS animations and transitions to settle before capture.
boolean
Request zero-data-retention processing. Enable only when this is configured for the organization; otherwise the provider rejects the request.
boolean
Exclude headers, footers, sidebars, and navigation from the output.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: CONTEXT_DEV_SEARCH_BRANDSPrefix-search Context.dev’s existing brand index by company name or domain and return up to 10 lightweight matches.Instant: Supported on the latest version.Instant pricing: $0.002 per brand searchDiscount: 100

Input Parameters

array
Up to 20 usage-tracking tags, each 1-50 characters.
string
required
Name or domain prefix to match, 1-100 characters; typo tolerance is not supported.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: CONTEXT_DEV_SEARCH_NEWSSearch current and historical news with a natural-language query or one company identified by name, domain, ticker, or ISIN. Returns one cursor-controlled page.Instant: Supported on the latest version.Instant pricing: From $0.002 per news search; more results cost more.Discount: 80

Input Parameters

array
Up to 20 usage-tracking tags, each 1-50 characters.
integer
Maximum articles in this page, from 1 to 100.
string
Opaque continuation cursor from the previous page; omit for the first page.
object
Company searches support newest (default) or relevance. Natural-language searches support relevance only; newest is rejected.
object
Optional filters: supply at most one category (article type, source domain, source country, or article language), plus an optional publication-date range.
string
required
Search all news by natural language or news about one company.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: CONTEXT_DEV_SEARCH_PEOPLESearch Context.dev’s people index by a natural-language description of role, employer, location, skills, or experience, with optional exact country and experience filters. Returns one relevance-ordered page of up to 10 people and an opaque continuation cursor. Restricted API keys must include the data:execute permission.Instant: Supported on the latest version.Instant pricing: $0.025 per nonempty people-search page; no-match searches are freeDiscount: 80

Input Parameters

array
Up to 20 usage labels for the Context.dev dashboard, each 1-50 characters.
string
required
Natural-language description of people to find by role, employer, location, skills, or experience; 1-500 characters.
string
Opaque next_cursor from the preceding page. Reuse it with exactly the same query and filters; omit for the first page.
object
Exact constraints that every returned person must satisfy in addition to the natural-language query.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not