Happy slice of mcp pizzaMCP.pizza

MCP

MCP.Pizza Chef: jina-ai

This tool connects your assistant directly to the live internet, so it can fetch and clean up webpages, search for current news, images, and academic papers, and even take screenshots of sites you want to reference. It works inside Claude Desktop, Cursor, and Windsurf, and can be added to other assistants through a small connector app. Basic page reading works without any account, though a free Jina API key unlocks web search, image search, and higher usage limits.

Data
Files/PDF
Web/Research

Use This MCP server To

Turn any webpage into clean, readable text Search the web for current news and information Search for images on any topic Find and read academic papers from arXiv Take a screenshot of any webpage Pull tables and figures out of a PDF Find out when a webpage was last updated

README

Jina AI Remote MCP Server

CLI version Install MCP Server Add MCP Server jina-mcp-server to LM Studio

A remote Model Context Protocol (MCP) server that provides access to Jina Reader, Embeddings and Reranker APIs with a suite of URL-to-markdown, web search, image search, and embeddings/reranker tools:

Tool Description Is Jina API Key Required?
primer Get current contextual information for localized, time-aware responses No
read_url Extract clean, structured content from web pages as markdown via Reader API Optional*
capture_screenshot_url Capture high-quality screenshots of web pages via Reader API Optional*
guess_datetime_url Analyze web pages for last update/publish datetime with confidence scores No
search_web Search the entire web for current information and news via Reader API Yes
search_arxiv Search academic papers and preprints on arXiv repository via Reader API Yes
search_ssrn Search academic papers on SSRN (Social Science Research Network) via Reader API Yes
search_images Search for images across the web (similar to Google Images) via Reader API Yes
search_jina_blog Search Jina AI news and blog posts at jina.ai/news No
search_bibtex Search for academic papers and return BibTeX citations (DBLP + Semantic Scholar) No
expand_query Expand and rewrite search queries based on the query expansion model via Reader API Yes
parallel_read_url Read multiple web pages in parallel for efficient content extraction via Reader API Optional*
parallel_search_web Run multiple web searches in parallel for comprehensive topic coverage and diverse perspectives via Reader API Yes
parallel_search_arxiv Run multiple arXiv searches in parallel for comprehensive research coverage and diverse academic angles via Reader API Yes
parallel_search_ssrn Run multiple SSRN searches in parallel for comprehensive social science research coverage via Reader API Yes
sort_by_relevance Rerank documents by relevance to a query via Reranker API Yes
classify_text Classify texts into user-defined labels via Embeddings API Yes
deduplicate_strings Get top-k semantically unique strings via Embeddings API and submodular optimization Yes
deduplicate_images Get top-k semantically unique images via Embeddings API and submodular optimization Yes
extract_pdf Extract figures, tables, and equations from PDF documents (arXiv papers or any PDF URL) using layout detection Yes

Optional tools work without an API key but have rate limits. For higher rate limits and better performance, use a Jina API key. You can get a free Jina API key from https://jina.ai

MCP FAQ

Can I use this to summarize a webpage instead of reading the whole thing myself?
Yes — ask your assistant to read the page first, and it will pull out clean, readable text that Claude, ChatGPT, or Gemini can then summarize for you.
Can I use this to find recent news on a topic?
Yes — you can ask your assistant to search the web, and it will return current results instead of relying only on what the AI already knows.
Do I need an account or an API key to use this?
Basic page reading and a few other features work without one, but a free Jina API key removes rate limits and unlocks web search, image search, and academic paper search.
Which apps does this work in?
It is built for Claude Desktop, Cursor, and Windsurf, and can also be connected to other assistants, such as ChatGPT or Codex, using a small connector tool.
How hard is it to set up?
You paste a short snippet into your app's settings — there is no coding or software installation required.
Can I search for images with this?
Yes — you can ask your assistant to search for images across the web, similar to a Google Images search.
Can it read PDF files?
Yes — it can pull text, tables, figures, and equations out of PDF documents, including academic papers.
Is there a cost to use this?
Connecting the tool itself is free, and a number of searches work without an account, but a free Jina API key is recommended for heavier, higher-volume use.