Jina

You can connect to a remote MCP server that exposes Jina Reader, Embeddings, and Reranker APIs. This setup lets your applications leverage a suite of tools for web, image, and content analysis, along with powerful search and content extraction capabilities. It’s useful when you want centralized access to these AI-powered services without hosting them locally.

How to use

Connect your MCP client to the remote server and reference the available tools by name. Use the provided HTTP endpoint for standard clients, or enable a local proxy if your client does not yet support remote MCP servers. When configuring your client, supply the server URL and, if required, your API key. You can mix and match tools such as reading web pages, searching the web, and extracting structured content from pages to build rich, context-aware workflows.

How to install

Prerequisites: Node.js and npm are installed on your machine. You may also need an API key from the service to access certain tools.

# 1) Install dependencies
npm install

# 2) Start the MCP server locally (if using a local dev server)
npm run start

Additional content

The server provides access to a wide range of tools, including contextual information, web and arXiv search, image search, content expansion, and parallel reading/searching capabilities. Each tool may require an API key for higher rate limits and better performance. Optional tools can be used without an API key but are rate-limited. For best results, combine search and read operations to verify sources.

Troubleshooting

If you encounter a tool calling loop, ensure you have sufficient context length configured in your model to accommodate the full tool calling chain and reasoning process. If you don’t see all tools, refresh your MCP client configuration to update tool definitions.

Developer and maintenance notes

To run and test locally, follow these steps: install dependencies, then start the development server. If you deploy to the cloud, you can expose an MCP endpoint for remote access and integrate it with your clients.

Available tools

primer

Get current contextual information for localized, time-aware responses

read_url

Extract clean, structured content from web pages as markdown via Reader API

capture_screenshot_url

Capture high-quality screenshots of web pages via Reader API

guess_datetime_url

Analyze web pages for last update/publish datetime with confidence scores

search_web

Search the entire web for current information and news via Reader API

search_arxiv

Search academic papers and preprints on arXiv repository via Reader API

search_images

Search for images across the web via Reader API

expand_query

Expand and rewrite search queries via the Reader API

parallel_read_url

Read multiple web pages in parallel for content extraction via Reader API

parallel_search_web

Run multiple web searches in parallel for topic coverage via Reader API

parallel_search_arxiv

Run multiple arXiv searches in parallel for comprehensive coverage via Reader API

sort_by_relevance

Rerank documents by relevance to a query via Reranker API

deduplicate_strings

Get top-k semantically unique strings via Embeddings API with submodular optimization

deduplicate_images

Get top-k semantically unique images via Embeddings API with submodular optimization