H|ψ⟩ Quantum Finance
Stock & Options Analytics for AI Agents
New Year 2027 Special$9.90/mo$19Save 48%Get New Year Offer →

Jina AI MCP Server

by Jina AIEndpoint responds

Jina AI's reader, search, embeddings and reranking tools for agents, from a hosted server.

Agent InfrastructureRemote (HTTP)API keyFree tierApache-2.0
Tools
12
Last checked
Nov 22, 2026
Listed
Nov 22, 2026
Unclaimed · from public sourcesReviewed by HPSILab · checked Nov 22, 2026Links reachable · checked Nov 22, 2026Endpoint responds · 12 tools · checked Nov 22, 2026

Install & connect

Third-party code: read it before you run it. HPSILab reviewed this guide but does not operate this server.

Install by client

claude mcp add --transport http jina-ai-mcp-server https://mcp.jina.ai/v1
Needs an API key: add it as the official guide below describes.

Generated by HPSILab from this listing's endpoint and package, in each client's documented format. The official guide decides arguments, keys and versions.

Official guide

# From the official README: https://github.com/jina-ai/MCP

# Remote server (API key optional)
claude mcp add -s user --transport http jina https://mcp.jina.ai/v1 \
  --header "Authorization: Bearer ${JINA_API_KEY}"

Remote endpoint

https://mcp.jina.ai/v1

Tools (12)

As listed by the server's public endpoint (tools/list), checked Nov 22, 2026. HPSILab never calls these tools.

Tool description check: no warning signs found

A rule-based check of the text for signs of prompt injection or unsafe requests. Not a security guarantee.

  • primer

    Current time, user location and network environment for the session. Use before answering anything time- or location-dependent.

  • guess_datetime_url

    Guess when a page was published or last updated, with a confidence score. Checks HTTP headers, metadata, Schema.org, visible dates, feeds and sitemaps.

    Parameters (1)
    • url · string · required
  • capture_screenshot_url

    Screenshot a page as base64 JPEG. Use when the page must be seen rather than read.

    Parameters (3)
    • url · string · required
    • firstScreenOnly · booleanCapture only the first screen instead of the full page. Faster.
    • return_url · booleanReturn URLs instead of base64 images.
  • read_url

    Fetch a URL (page or PDF) as clean markdown. Pass `question` to get only the passages answering it instead of the whole page - far cheaper than reading the full body into context.

    Parameters (8)
    • url · requiredPage or PDF URL, or up to 5 URLs to read in parallel.
    • withAllLinks · booleanAlso return every link on the page.
    • withAllImages · booleanAlso return every image on the page.
    • question · stringReturn only the passages answering this question, instead of the full body. Omit for the whole page.
    • chunk_size · integerPassage size in words, default 100. Larger gives more surrounding context, smaller pinpoints the answer. Comparable across scripts. Needs `question`.
    • topk · integerPassages to return, default 1. Needs `question`.
    • ocr · booleanRead the rendered page as an image with jina-ocr-v1 instead of its HTML. Use for scanned documents and PDFs whose text is not in the markup, and to keep formulas and table structure. Parses ONE page per call, page 1 unless `page` says otherwise, and costs about 40x the tokens per page, so leave off unless the HTML path has failed you.
    • page · integerWhich page the OCR pass should parse, 1-based. Needs `ocr`; the HTML path returns the whole document at once.
  • search_web

    Search the web. Returns titles, URLs and search-engine snippets.

    Parameters (6)
    • query · required
    • num · integer
    • tbs · stringAge limit: qdr:h, qdr:d, qdr:w, qdr:m, qdr:y (hour to year).
    • location · string
    • gl · stringCountry code, e.g. 'de'.
    • hl · stringLanguage code, e.g. 'zh-cn'.
  • search_arxiv

    Search arXiv preprints (physics, maths, CS, quantitative biology and finance).

    Parameters (3)
    • query · required
    • num · integer
    • tbs · stringAge limit: qdr:h, qdr:d, qdr:w, qdr:m, qdr:y (hour to year).
  • search_ssrn

    Search SSRN working papers (social science, economics, law, finance, management).

    Parameters (3)
    • query · required
    • num · integer
    • tbs · stringAge limit: qdr:h, qdr:d, qdr:w, qdr:m, qdr:y (hour to year).
  • search_jina_blog

    Search Jina AI's news and blog at jina.ai/news: product announcements, model releases, technical write-ups.

    Parameters (3)
    • query · required
    • num · integer
    • tbs · stringAge limit: qdr:h, qdr:d, qdr:w, qdr:m, qdr:y (hour to year).
  • search_images

    Search the web for images. Returns base64 JPEGs by default.

    Parameters (7)
    • query · string · required
    • num · integer
    • return_url · booleanReturn URLs and metadata instead of base64 images.
    • tbs · stringAge limit: qdr:h, qdr:d, qdr:w, qdr:m, qdr:y (hour to year).
    • location · string
    • gl · stringCountry code, e.g. 'de'.
    • hl · stringLanguage code, e.g. 'zh-cn'.
  • sort_by_relevance

    Rerank documents by relevance to a query, using Jina Reranker.

    Parameters (3)
    • query · string · required
    • documents · array · requiredDocuments to rank, up to 1024.
    • top_n · integer
  • deduplicate_strings

    Select the top-k semantically distinct strings from a list, dropping near-duplicates.

    Parameters (2)
    • strings · array · requiredStrings to deduplicate, up to 1000.
    • k · integerHow many to keep. Omit to pick k automatically from diminishing returns.
  • extract_pdf

    Extract figures, tables and equations from a PDF as images, by arXiv id or URL.

    Parameters (4)
    • id · stringarXiv id, e.g. '2301.12345'. Give id or url.
    • url · stringPDF URL on arxiv.org, ssrn.com, openreview.net or aclanthology.org; other hosts are refused. Give id or url.
    • max_edge · numberLongest image edge in pixels, default 1024.
    • type · stringComma-separated types to keep: figure, table, equation. Default all.

Links

More Agent Infrastructure MCP servers

  • Hyperbrowser MCP Server

    Scrape, crawl and extract structured data, or run browser agents, through Hyperbrowser's cloud browsers.

  • Oxylabs MCP Server

    Scrape and parse web pages, including JavaScript-heavy and geo-restricted sites, with Oxylabs.

  • Bright Data MCP Server

    Real-time web data for agents: search, scrape and browse sites without getting blocked, through Bright Data.

  • Langfuse Prompt Management MCP

    Fetch and use prompts managed in Langfuse, so agents and apps share versioned prompt templates.

  • Docker MCP Gateway

    Docker's gateway for running and managing MCP servers in isolated containers, with a shared catalog and secrets.

  • Apify MCP Server

    Run thousands of ready-made Apify Actors for web scraping, crawling and data extraction from your AI client.

All Agent Infrastructure MCP servers →
← All MCP servers