‹ Back to apps
H
Hydrafetch
Turn any URL into clean Markdown and structured data your agent can use. Scrape, crawl, search and extract through one API. One credit a page, failures free.
What’s inside
1 MCP server · 6 skills- Skillbuild-a-dataset# Skill: Build a dataset from the web ## What this skill does Turns a question into a table: find the pages, fetch them at volume, and pull the same fields from each. Uses queued jobs rather than a
- Skillextract-structured-data# Skill: Extract typed data from pages ## What this skill does Pulls typed, schema-shaped JSON out of one or more web pages, so you get fields you can rely on rather than prose you have to parse. #
- Skillresearch-a-company# Skill: Research a company from its domain ## What this skill does Builds a picture of a company from nothing but its domain: who they are, what they look like, what they sell, and what they have p
- Skillscrape-for-context# Skill: Scrape a page for LLM context ## What this skill does Turns a URL into clean markdown suitable for putting in a model's context: navigation, banners, cookie notices and boilerplate removed,
- Skillshow-a-company-logo# Skill: Show a company logo ## What this skill does Puts a real company logo next to a company name, from nothing but a domain. This is the most common thing anyone needs from company data and the
- Skillwhere-to-use-hydrafetch# Skill: Find where Hydrafetch fits in a codebase ## What this skill does Reads a project and reports where Hydrafetch would replace something fragile, and where it would add something the project c
- MCP serverhydrafetchRemote MCP server: scrape, map, search, extract, brand, logo, styleguide, screenshot and images. Streamable HTTP, OAuth or bearer key.