MCP SERVER · OFFICIAL PROJECT22 tools for research: read and search the web, arXiv and SSRN, run them in parallel, then rerank, dedupe and classify what comes back.
LABSCO SUMMARY
Every research agent hits the same wall: parallel search returns a mass of near-identical passages, and reading them all is unaffordable. Having reranking and semantic deduplication as callable tools — rather than something the model attempts by reading — turns that mass into a shortlist before it enters the context. guess_datetime_url is the other quiet favourite: knowing when a page was actually published is the check most agents skip.
Jina's official endpoint, which lists 22 tools at version 1.7.0. It is a complete research pipeline — retrieval, parallel retrieval, and then the embedding operations that make a large result set usable.
A Jina API key is optional. The parallel and embedding tools are what most benefit from a paid quota.
Paste a URL — add the endpoint to your client
USE CASES
Expand the query, run parallel searches, then rerank and deduplicate before reading anything.
Deep search reads each result and returns the passage that answers the question.
Search arXiv and SSRN, and get BibTeX citations for what you cite.
Extract figures, tables and equations from the PDF by layout rather than by text.
Guess a page's published or updated date from headers and markup.
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
capture_screenshot_urlCapture 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.
classify_textClassify texts into user-defined labels using Jina embeddings. Use this when you need to categorize, tag, or sort text content into predefined categories. Perfect for sentiment analysis, topic classification, content moderation, or any text categorization task.
deduplicate_imagesGet 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.
deduplicate_stringsGet 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.
expand_queryExpand 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.
extract_pdfExtract 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.
guess_datetime_urlGuess 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.
parallel_read_urlRead 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.
parallel_search_arxivRun 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.
parallel_search_ssrnRun 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.
parallel_search_webRun 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.
primerGet 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.
read_urlExtract 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.
search_arxivSearch 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.
search_bibtexSearch for academic papers and return BibTeX citations. Searches DBLP (computer science) and Semantic Scholar (broad academic coverage) for comprehensive results. Returns formatted BibTeX entries ready to use in LaTeX documents.
search_imagesSearch 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.
search_jina_blogSearch 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.
search_ssrnSearch 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.
search_webSearch 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.
search_web_deepSearch the web, then read the result pages and return the passage from each that best answers the query, re-ranked by relevance. Regular search_web returns only the search engine's snippet, which is often a page fragment that does not answer the question; this reads the page itself and extracts a paragraph-length passage (~100 words). Best for questions whose answer is buried in page content rather than in titles or descriptions. Slower than search_web (typically 2-20s). Each result carries a snippet_source field: 'content' when the snippet came from the page body, 'serp' when the search engine's own snippet scored higher and was kept instead.
show_api_keyReturn the bearer token from the Authorization header of the MCP settings, which is used to debug.
sort_by_relevanceRerank 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.
BEFORE YOU INSTALL
22 tools when we connected.
an MCP client that can reach a remote endpoint
Optional — the endpoint works without a key but is rate-limited; an API key sent as Authorization: Bearer unlocks more
CONTEXT COST
Rated by the size of the 22 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Add the endpoint to your client.
https://mcp.jina.ai/sseMCP servers
JoeBuildsStuff
keptlive
telly6