Jina AI Remote MCP Server
Provides tools for searching academic papers and preprints on the arXiv repository, enabling access to scholarly research content
Supports deployment of the MCP server to Cloudflare Workers for serverless hosting
Offers image search capabilities similar to Google Images for finding and retrieving web images
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Jina AI Remote MCP Server search the web for latest AI developments in 2024"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Jina AI Remote MCP Server
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? |
| Get current contextual information for localized, time-aware responses | No |
| Extract clean, structured content from web pages as markdown via Reader API | Optional* |
| Capture high-quality screenshots of web pages via Reader API | Optional* |
| Analyze web pages for last update/publish datetime with confidence scores | No |
| Search the entire web for current information and news via Reader API | Yes |
| Search academic papers and preprints on arXiv repository via Reader API | Yes |
| Search for images across the web (similar to Google Images) via Reader API | Yes |
| Expand and rewrite search queries based on the query expansion model via Reader API | Yes |
| Read multiple web pages in parallel for efficient content extraction via Reader API | Optional* |
| Run multiple web searches in parallel for comprehensive topic coverage and diverse perspectives via Reader API | Yes |
| Run multiple arXiv searches in parallel for comprehensive research coverage and diverse academic angles via Reader API | Yes |
| Rerank documents by relevance to a query via Reranker API | Yes |
| Get top-k semantically unique strings via Embeddings API and submodular optimization | Yes |
| Get top-k semantically unique images via Embeddings API and submodular optimization | 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
Usage
For client that supports remote MCP server:
{
"mcpServers": {
"jina-mcp-server": {
"url": "https://mcp.jina.ai/sse",
"headers": {
"Authorization": "Bearer ${JINA_API_KEY}" // optional
}
}
}
}For client that does not support remote MCP server yet, you need mcp-remote a local proxy to connect to the remote MCP server.
{
"mcpServers": {
"jina-mcp-server": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.jina.ai/sse"
// optional bearer token
"--header",
"Authorization: Bearer ${JINA_API_KEY}"
]
}
}
}Related MCP server: Jina AI Remote MCP Server
Troubleshooting
I got stuck in a tool calling loop - what happened?
This is a common issue with LMStudio when the default context window is 4096 and you're using a thinking model like gpt-oss-120b or qwen3-4b-thinking. As the thinking and tool calling continue, once you hit the context window limit, the AI starts losing track of the beginning of the task. That's how it gets trapped in this rolling context window.
The solution is to load the model with enough context length to contain the full tool calling chain and thought process.

I can't see all tools.
Some MCP clients have local caching and do not actively update tool definitions. If you're not seeing all the available tools or if tools seem outdated, you may need to remove and re-add the jina-mcp-server to your MCP client configuration. This will force the client to refresh its cached tool definitions. In LMStudio, you can click the refresh button to load new tools.

Claude Desktop says "Server disconnected" on Windows
Cursor and Claude Desktop (Windows) have a bug where spaces inside args aren't escaped when it invokes npx, which ends up mangling these values. You can work around it using:
{
// rest of config...
"args": [
"mcp-remote",
"https://mcp.jina.ai/sse",
"--header",
"Authorization:${AUTH_HEADER}" // note no spaces around ':'
],
"env": {
"AUTH_HEADER": "Bearer <JINA_API_KEY>" // spaces OK in env vars
}
},Cursor shows a red dot on this MCP status
Likely a UI bug from Cursor, but the MCP works correctly without any problem. You can toggle off/on to "restart" the MCP if you find the red dot annoying (fact is, since you are using this as a remote MCP, it's not a real "server restart" but mostly a local proxy restart).

My LLM never uses some tools
Assuming all tools are enabled in your MCP client but your LLM still never uses some tools, it's likely your LLM favors some tools over others, which is pretty common when an LLM is trained with a specific set of tools. For example, we rarely see parallel_* tools being used organically by LLMs unless they are explicitly instructed to do so. In Cursor, you can add the following rule to your .mdc file:
---
alwaysApply: true
---
When you are uncertain about knowledge, or the user doubts your answer, always use Jina MCP tools to search and read best practices and latest information. Use search_arxiv and read_url together when questions relate to theoretical deep learning or algorithm details. search_web and search_arxiv cannot be used alone - always combine with read_url or parallel_read_url to read from multiple sources. Remember: every search must be complemented with read_url to read the source URL content. For maximum efficiency, use parallel_* versions of search and read when necessary.Developer Guide
Local Development
# Clone the repository
git clone https://github.com/jina-ai/MCP.git
cd MCP
# Install dependencies
npm install
# Start development server
npm run startDeploy to Cloudflare Workers
This will deploy your MCP server to a URL like: jina-mcp-server.<your-account>.workers.dev/sse
Available Tools
19 toolscapture_screenshot_urlA
Capture high-quality screenshots of web pages in base64 encoded JPEG format. Use this tool when you need to visually inspect a website, take a snapshot for analysis, or show users what a webpage looks like.
Inputs: url (required), firstScreenOnly, return_url.
deduplicate_imagesA
Get top-k semantically unique images (URLs or base64-encoded) using Jina CLIP v2 embeddings and submodular optimization. Use this when you have many visually similar images and want the most diverse subset.
Inputs: images (required), k.
deduplicate_stringsA
Get top-k semantically unique strings from a list using Jina embeddings and submodular optimization. Use this when you have many similar strings and want to select the most diverse subset that covers the semantic space. Perfect for removing duplicates, selecting representative samples, or finding diverse content.
Inputs: strings (required), k.
expand_queryB
Expand and rewrite search queries based on an up-to-date query expansion model. This tool takes an initial query and returns multiple expanded queries that can be used for more diversed and deeper searches. Useful for improving deep research results by searching broader and deeper.
Inputs: query (required).
extract_pdfA
Extract figures, tables, and equations from PDF documents using layout detection. Perfect for extracting visual elements from academic papers on arXiv or any PDF URL. Returns base64-encoded images of detected elements with metadata.
Inputs: id, url, max_edge, type.
guess_datetime_urlA
Guess the last updated or published datetime of a web page. This tool examines HTTP headers, HTML metadata, Schema.org data, visible dates, JavaScript timestamps, HTML comments, Git information, RSS/Atom feeds, sitemaps, and international date formats to provide the most accurate update time with confidence scores. Returns the best guess timestamp and confidence level.
Inputs: url (required).
parallel_read_urlA
Read multiple web pages in parallel to extract clean content efficiently. For best results, provide multiple URLs that you need to extract simultaneously. This is useful for comparing content across multiple sources or gathering information from multiple pages at once.
Inputs: urls (required), timeout.
parallel_search_arxivA
Run multiple arXiv searches in parallel for comprehensive research coverage and diverse academic angles. For best results, provide multiple search queries that explore different research angles and methodologies. You can use expand_query to help generate diverse queries, or create them yourself.
Inputs: searches (required), timeout.
parallel_search_ssrnB
Run multiple SSRN searches in parallel for comprehensive social science research coverage and diverse academic angles. For best results, provide multiple search queries that explore different research angles and methodologies. You can use expand_query to help generate diverse queries, or create them yourself.
Inputs: searches (required), timeout.
parallel_search_webA
Run multiple web searches in parallel for comprehensive topic coverage and diverse perspectives. For best results, provide multiple search queries that explore different aspects of your topic. You can use expand_query to help generate diverse queries, or create them yourself.
Inputs: searches (required), timeout.
primerA
Get up-to-date contextual information of the current session to provide localized, time-aware responses. Use this when you need to know the current time, user's location, or network environment to give more relevant and personalized information.
Inputs: no named parameters.
read_urlA
Extract and convert web page content to clean, readable markdown format. Perfect for reading articles, documentation, blog posts, or any web content. Use this when you need to analyze text content from websites, bypass paywalls, or get structured data.
Inputs: url (required), withAllLinks, withAllImages.
search_arxivA
Search academic papers and preprints on arXiv repository. Perfect for finding research papers, scientific studies, technical papers, and academic literature. Use this when researching scientific topics, looking for papers by specific authors, or finding the latest research in fields like AI, physics, mathematics, computer science, etc.
Inputs: query (required), num, tbs.
search_imagesA
Search for images across the web, similar to Google Images. Use this when you need to find photos, illustrations, diagrams, charts, logos, or any visual content. Perfect for finding images to illustrate concepts, locating specific pictures, or discovering visual resources. Images are returned by default as small base64-encoded JPEG images.
Inputs: query (required), return_url, tbs, location, +2 more.
search_jina_blogA
Search Jina AI news and blog posts at jina.ai/news for articles about AI, machine learning, neural search, embeddings, and Jina products. Use this to find official Jina documentation, tutorials, product announcements, and technical deep-dives.
Inputs: query (required), num, tbs.
search_ssrnA
Search academic papers and preprints on SSRN (Social Science Research Network). Perfect for finding research papers in social sciences, economics, law, finance, accounting, management, and humanities. Use this when researching social science topics, looking for working papers, or finding the latest research in business and economics fields.
Inputs: query (required), num, tbs.
search_webA
Search the entire web for current information, news, articles, and websites. Use this when you need up-to-date information, want to find specific websites, research topics, or get the latest news. Ideal for answering questions about recent events, finding resources, or discovering relevant content.
Inputs: query (required), num, tbs, location, +2 more.
show_api_keyB
Return the bearer token from the Authorization header of the MCP settings, which is used to debug.
Inputs: no named parameters.
sort_by_relevanceA
Rerank a list of documents by relevance to a query using Jina Reranker API. Use this when you have multiple documents and want to sort them by how well they match a specific query or topic. Perfect for document retrieval, content filtering, or finding the most relevant information from a collection.
Inputs: query (required), documents (required), top_n.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 19 tools
Most tools have distinct purposes with clear boundaries, such as capture_screenshot_url for visual snapshots, read_url for text extraction, and search_web for web searches. However, some overlap exists between parallel_search_web and search_web, where the parallel version is for multiple queries but could be confused with the single-query version, and between deduplicate_images and deduplicate_strings, which share a similar semantic deduplication concept but target different data types, potentially causing minor confusion.
Tool names follow a highly consistent snake_case verb_noun pattern throughout, such as capture_screenshot_url, read_url, search_web, and deduplicate_images. This predictability makes it easy for agents to understand and select tools based on their naming conventions, with no deviations or mixed styles observed.
With 19 tools, the count is slightly high but reasonable for a server focused on web and academic research tasks, covering areas like content extraction, search, deduplication, and analysis. It provides comprehensive functionality without being overwhelmingly bloated, though it borders on being heavy for a single domain.
The tool set offers complete coverage for web and academic research workflows, including content extraction (read_url, extract_pdf), search across multiple sources (web, arXiv, SSRN), deduplication (images, strings), query expansion, relevance sorting, and utility functions like datetime guessing and API key display. There are no obvious gaps, and tools support each other effectively, such as expand_query feeding into parallel searches.
Related MCP Connectors
Web data for agents. Extract web pages, crawl websites, discover URLs, and search the web.
Web knowledge fetching tools for your agent.
Web search and page reading for AI agents, including JSON APIs, RSS feeds and YouTube.
Public web tools for agents: product extraction, claim checks, webpage QA and ranked audits.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables web content retrieval and semantic search capabilities through the Jina AI API. Provides tools to fetch content from URLs and perform intelligent web searches with natural language queries.3MIT
- AlicenseNot gradedqualityDmaintenanceProvides access to Jina's web search, content extraction, image search, and AI-powered reranking tools through a comprehensive suite of URL processing and semantic analysis capabilities. Enables users to search the web, extract clean markdown from URLs, capture screenshots, search academic papers, and perform advanced text/image deduplication with embeddings.Apache 2.0
- AlicenseNot gradedqualityNot gradedmaintenanceProvides access to Jina AI's suite of tools including web search, URL reading, image search, embeddings, and reranking capabilities. Enables users to extract web content as markdown, search academic papers, capture screenshots, and perform semantic operations through natural language.-
- AlicenseNot gradedqualityNot gradedmaintenanceProvides access to Jina AI's web reading, search, embeddings, and reranking capabilities. Enables URL content extraction, web/arXiv/image search, document deduplication, and relevance ranking through natural language.Apache 2.0