Context.dev
for LuumenAI

Pull web pages, documents, and brand data into your terminal as clean text

Connect Context.dev with an API key and ask for what is on a page. CONTEXT_DEV_SCRAPE_WEBPAGE_MARKDOWN returns one public URL as Markdown. CONTEXT_DEV_EXTRACT_STRUCTURED_WEB_DATA crawls a site and returns fields matching a JSON Schema you supply. CONTEXT_DEV_PARSE_FILE turns an uploaded document into readable text. You can also check monitors, batches, and WebDB usage on the connected account. These tools are read-only, so answers come back immediately.

The Context.dev toolbox

11 tools, all read-only. They answer instantly, and every call is logged.

  • ReadExtract Structured Web DataCrawl relevant pages from a website and return data matching a caller-provided JSON Schema and extraction instructions.
  • ReadGet BrandRetrieve enriched brand identity, logos, colors, industry, and description using exactly one domain, name, work email, ticker, direct URL, or transaction descriptor.
  • ReadGet Monitor LimitsReturn the connected account's plan and current monitor usage versus its monitor limit.
  • ReadGet WebDB UsageReturn WebDB credit balance, period consumption, row count, storage, and per-collection usage for an optional time range.
  • ReadGet Website StyleguideExtract a website's colors, typography, spacing, shadows, font assets, and common component styles from either a domain or one direct URL.
  • ReadList BatchesList and filter the connected account's asynchronous web batches from newest to oldest, returning one cursor-controlled page.
  • ReadList MonitorsList and filter the connected organization's web monitors, returning one cursor-controlled page.
  • ReadList 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.
  • ReadParse FileConvert an uploaded document, image, source file, or data file into LLM-usable Markdown.
  • ReadScrape Webpage to MarkdownRender one public URL and return its main or CSS-selected content as Markdown.
  • ReadSearch BrandsPrefix-search Context.dev's existing brand index by company name or domain and return up to 10 lightweight matches.

Questions

How does LuumenAI connect to Context.dev?

Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

Can LuumenAI change things in Context.dev on its own?

No. Every one of the 11 tools LuumenAI has for Context.dev is read-only, so it can answer questions from Context.dev but cannot change anything in it. Reads are not gated — they answer immediately, and each one is recorded on the audit trail with the actor and the result.

Who gets access to the integration?

You decide. Access is granted per agent, skill, and team, and per environment — production is not staging.

Is there an audit trail?

Every call to Context.dev is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.

Put Context.dev to work with Luumen

Connect in minutes. Every action scoped, approved, and audited from day one.