Web reader and search API for AI pipelines. Converts any URL to clean markdown, runs grounded search, and powers RAG at scale — no browser automation needed.
Skills
URL to Markdown
Convert any URL into clean, LLM-ready markdown in one API call, removing ads, nav, and boilerplate
Grounded Search
Run search queries with real-time web grounding to reduce LLM hallucinations in answers
Batch Crawl
Crawl entire sites or URL lists in parallel and return structured markdown output for pipelines
Embed & Rerank
Generate embeddings and rerank passages with Jina Embeddings v3 and Reranker v2 APIs
MCP Integration
Access Reader and Search via Model Context Protocol for Claude and MCP-compatible agents
Related Agents
ScrapeGraphAI
Scrapes websites from a natural-language description of the data you want, building the extraction graph automatically…
Crawl4AI
Crawls and scrapes web pages into clean Markdown for RAG pipelines, with CSS, XPath, and LLM-driven structured extracti…
LightRAG
Builds a graph-based retrieval index over documents so agents can answer questions spanning many sources, served throug…
context.dev
Scrapes, crawls and searches the web for agents through a REST API, SDKs, CLI and hosted MCP server, returning LLM-read…