Scrape, extract, and understand the web, plus identify any company from a domain, email, name, or transaction string. This MCP server exposes Context.dev's API for web scraping in multiple formats (raw HTML, Markdown, screenshots, images, sitemaps, and web search), schema-driven structured data extraction, design-system extraction (styleguides and fonts), and brand intelligence lookups. It's built for AI agents that read, summarize, or monitor web content, for enriching CRM, KYC, or fintech pipelines with company and brand data, and for extracting a competitor's design system or structured product and pricing data at scale.
Hermes is Nous Research's command-line agent. MCP servers are declared in its YAML config and reloaded without a restart.
This guide connects Context.dev to Hermes through MewCP, so Hermes can use Context.dev's 13 tools, like scrape_html, scrape_markdown and scrape_screenshot, without your Context.dev credentials ever reaching the app.
Your Context.dev API key is stored encrypted and injected only at call time. Your agent never holds it, so it can never leak it, log it or paste it into a prompt.
More apps
Crawl websites and extract clean structured data optimized for AI applications and automation. Collect content from the web at scale while maintaining high-quality outputs.
Extract structured data from websites and public web pages. Fetch content, parse information and transform online data into formats that can be consumed by applications, agents and workflows.
TinyFish MCP for running AI-driven browser automation tasks, deep web research, persistent browser login profiles, remote CDP browser sessions, and agentic wallet payments.
Google Maps provides location intelligence and place discovery through geocoding, nearby searches, place details, directions, and route calculations. Find businesses and points of interest, retrieve addresses and coordinates, compare travel routes, and explore geographic information using Google Maps data.
Other clients
Context.dev works the same way in every client below. Pick yours for its own guide.
Free to start.
Scope access to the exact Context.dev tools and accounts you allow, work and personal side by side. Anything outside that scope is refused at call time, even when the model asks for it.
Each call is logged: what ran, on which account, and whether it worked. Failures come back structured, so the agent knows whether to retry instead of guessing.
Every app sits behind one secure MCP URL, and there is no server for you to deploy or keep running. Add an integration in the dashboard and it is live on the next call, with no config to change and no new credentials to wire up. Tools load only when a task needs them, so your agent stays fast and focused however many apps you connect.
Edit config.yaml in your Hermes config directory (~/.hermes).
Put this under the top-level "mcp_servers:" key.
Run /reload-mcp in Hermes, or start a fresh session. Sign in when the browser window opens.
Start a new chat and ask: "List the tools you can use from MewCP." You should see your connected apps.
Scrape a URL and return its raw HTML content. Supports web pages, PDFs, XML, JSON, Markdown, CSV, and SVG files.
Scrape a URL and return its content converted to clean, LLM-ready Markdown. Strips boilerplate and preserves headings, links, and structure.
Capture a visual screenshot of a website. Provide either 'domain' for the homepage or 'direct_url' for a specific page. Returns a URL to the screenshot image.
Collect all images from a URL: img tags, SVGs, CSS backgrounds, video posters, and meta images. Returns each image's src, element type, and optional metadata.
Discover all pages on a website by crawling its XML sitemaps. Returns a list of URLs up to maxLinks (default 10,000).
Search the web with a natural-language query. Optionally scrapes each result page to Markdown for deeper content. Returns ranked results with url, title, description, and relevance.
Retrieve rich brand data for a company domain: logos, colors, backdrops, description, social links, address, stock ticker, and industry classification.
Retrieve brand data for the company associated with an email address. Returns an error for free (Gmail, Outlook) or disposable email addresses.
Retrieve brand data for a company by its name. Useful when only the company name is known. Name must be 3–30 characters.
Identify a company from a bank transaction description or merchant string (e.g. 'AMZN*123456', 'UBER* EATS', 'SQ *COFFEE SHOP'). Returns full brand data.
Crawl a website and extract structured data conforming to a JSON Schema. Ideal for scraping product info, pricing tables, contact details, team pages, or any structured content. Up to 50 pages per call.
Extract a website's design system: brand colors, typography (font families, sizes, weights), element spacing, shadows, button styles, and font CDN links.
Extract all font families used on a website along with usage statistics, CSS selectors, fallback fonts, and CDN asset links (Google Fonts or custom).
