Jina AI Remote

You can access Jina Reader, Embeddings, and Reranker capabilities remotely through an MCP server, combining powerful tools for reading web content, searching information, and computing semantic relationships. This server exposes a curated set of endpoints and tools that you can connect to from MCP clients to enable scalable, web-enabled AI workflows.

How to use

Connect your MCP client to the remote server using either the HTTP endpoint for a direct remote connection or a local proxy that forwards to the remote MCP. The server exposes a suite of tools for content extraction, web and image search, academic search, and deduplication, all designed to work with large language models.

How to install

Prerequisites you should have before starting:
- Node.js and npm installed on your machine
- A valid Jina API key if you plan to use API-key protected endpoints
- Access to the internet to reach the remote MCP URL

Choose one of the two connection methods shown below. Use the HTTP method for a direct remote connection or the local proxy method if your client requires it.

{
  "mcpServers": {
    "jina-mcp-server": {
      "url": "https://mcp.jina.ai/v1",
      "headers": {
        "Authorization": "Bearer ${JINA_API_KEY}" // optional
      }
    }
  }
}

Notes on configuration and usage

If your client does not support remote MCP servers yet, you can use a local proxy to connect to the remote MCP server.

{
  "mcpServers": {
    "jina-mcp-server": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://mcp.jina.ai/v1",
        "--header",
        "Authorization: Bearer ${JINA_API_KEY}"
      ]
    }
  }
}

Security and API key usage

For endpoints protected by an API key, provide your key in the Authorization header as a Bearer token. Replace ${JINA_API_KEY} with your actual key in client configurations.

Tools available through the MCP server

The server offers a range of tools to query, read, and analyze content from the web, scholarly sources, and image repositories, plus utilities to expand queries and deduplicate results.

Tool usage tips

Some tools do not require an API key, while others require a key with higher rate limits for best performance. When composing requests, you can pass single queries or arrays to enable parallel execution where supported.

Troubleshooting common issues

If you encounter a tool calling loop or missing tools in your client, refresh or reconfigure the MCP connection to ensure the latest tool definitions are loaded.

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 via Reader API

search_ssrn

Search academic papers on SSRN via Reader API

search_images

Search for images across the web via Reader API

search_jina_blog

Search Jina AI news and blog posts at jina.ai/news

search_bibtex

Return BibTeX citations for academic papers (DBLP + Semantic Scholar)

expand_query

Expand and rewrite search queries based on the query expansion model via Reader API

parallel_read_url

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

parallel_search_web

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

parallel_search_arxiv

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

parallel_search_ssrn

Run multiple SSRN searches in parallel for comprehensive social science coverage via Reader API

sort_by_relevance

Rerank documents by relevance via Reranker API

deduplicate_strings

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

deduplicate_images

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

extract_pdf

Extract figures, tables, and equations from PDFs using layout detection