Jina AI MCP server

Endpoint: https://mcp.jina.ai/v1 · Authentication: No auth

Jina Reader, web, arXiv, and image search, screenshot, PDF extraction, and reranking tools. Some tools work without a key; an optional Jina API key raises limits and unlocks the rest.

Test it live Run the release-readiness report

How do I authenticate?

Add the endpoint directly in your client. The catalog records no authentication requirement; no OAuth sign-in or API key is configured in this setup. The live server may change.

Authentication and connection guide

Connection specification

Remote endpoint: https://mcp.jina.ai/v1
Browser access: Not yet measured
Declared MCP transport: Streamable HTTP
Live-validated MCP transport: Streamable HTTP — Observed by the latest catalog validation
Declared authentication: No authentication
Detected authentication: No authentication detected or retained from publisher evidence
Alternative authentication: Bearer token
Protocol lifecycle: Stateful MCP · 2025-11-25
Required header: Authorization — Optional Jina API key: Bearer <JINA_API_KEY>
Category: Search

Product documentation · Source repository · Official listing documentation

More Search MCP servers · Browse all MCP servers · Test this endpoint in the MCP Playground

Authorization setup

No app registration needed

This catalog entry does not require authorization or provider app registration.

Connect it

Live-validated endpoint: https://mcp.jina.ai/v1 · Streamable HTTP. No authentication is required by the catalog listing.

Agent prompt for Claude Code or Codex

Add the Jina AI MCP server to my MCP client configuration and verify that it works.

What it is: Jina Reader, web, arXiv, and image search, screenshot, PDF extraction, and reranking tools. Some tools work without a key; an optional Jina API key raises limits and unlocks the rest.
Server URL: https://mcp.jina.ai/v1
Transport: Streamable HTTP (remote MCP server, no local install).
Authentication: none. The server accepts connections without credentials.
Tools (12, as last observed by mcptest): capture_screenshot_url, deduplicate_strings, extract_pdf, guess_datetime_url, primer, read_url, search_arxiv, search_images, search_jina_blog, search_ssrn, search_web, sort_by_relevance.
Reference: https://mcptest.io/servers/jina/

Steps:
1. Work out which MCP client I use (Claude Code, Codex, Cursor, VS Code or another) and add the server under the name "jina" in that client's MCP configuration, user scope unless I ask otherwise.
   Claude Code: claude mcp add --transport http --scope user 'jina' 'https://mcp.jina.ai/v1'
   Codex: codex mcp add 'jina' --url 'https://mcp.jina.ai/v1'
   Other clients: use the setup for that client on the reference page.
2. Never write a credential value into a file that could be committed; reference an environment variable or the client's secret store, and ask me for any value you need.
3. Verify: connect to the server and call tools/list. Confirm the tools above are listed, and report any sign-in step I still have to complete.

Claude Code setup

Run in a terminal. This user-scoped entry is available across projects.

claude mcp add --transport http --scope user 'jina' 'https://mcp.jina.ai/v1'

Codex CLI setup

Run in a terminal; Codex stores the entry in ~/.codex/config.toml.

codex mcp add 'jina' --url 'https://mcp.jina.ai/v1'

Cursor setup

Add to .cursor/mcp.json for this project, or ~/.cursor/mcp.json for all projects.

{
  "mcpServers": {
    "jina": {
      "url": "https://mcp.jina.ai/v1"
    }
  }
}

VS Code setup

Add to .vscode/mcp.json, or run “MCP: Open User Configuration” for a private user-level entry.

{
  "servers": {
    "jina": {
      "type": "http",
      "url": "https://mcp.jina.ai/v1"
    }
  }
}

Claude setup

Add the endpoint above in Claude:

Customize > Connectors > Add custom connector
Team/Enterprise: Organization settings > Connectors > Add > Custom > Web

Claude Desktop setup

Add the endpoint above in Claude Desktop:

Remote: Customize > Connectors (same as claude.ai)
Local: Settings > Developer > Edit Config, or Settings > Extensions for .mcpb files
~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), local servers only

ChatGPT setup

Add the endpoint above in ChatGPT:

ChatGPT web: Plugins > Add custom MCP server, then configure authentication and accept the risk warning

Windsurf setup

Add the endpoint above in Windsurf:

~/.config/devin/mcp_config.json (%APPDATA%\devin\mcp_config.json on Windows), serverUrl or url
Cascade panel > ... > MCPs > Open MCP config file

Gemini CLI setup

Add the endpoint above in Gemini CLI:

gemini mcp add --transport http <name> <url>
~/.gemini/settings.json (user) or .gemini/settings.json (project), mcpServers

MCP SDK setup

Add the endpoint above in MCP SDK:

Programmatic: new Client(...).connect(new StreamableHTTPClientTransport(url))

Notes for every client

Optional bearer token alternative: Store JINA_API_KEY in your operating system keychain, secret manager, or protected environment; never commit the value. The Authorization header syntax is Bearer <JINA_API_KEY>.

Client compatibility

Client	Status	Why
Claude Code	Supported	Claude Code supports Streamable HTTP servers and servers without authentication or bearer-token headers.
Codex	Supported	Codex supports Streamable HTTP servers and servers without authentication or bearer-token headers.
Cursor	Supported	Cursor supports Streamable HTTP servers and servers without authentication or bearer-token headers.
VS Code	Supported	VS Code supports Streamable HTTP servers and servers without authentication or bearer-token headers.
Claude	Supported	Claude supports Streamable HTTP servers and servers without authentication or bearer-token headers.
Claude Desktop	Supported	Claude Desktop supports Streamable HTTP servers and servers without authentication or bearer-token headers.
ChatGPT	Partial	Stateful routing needs operational care: ChatGPT can preserve MCP sessions, but the deployment must route a session consistently and retain its state.
Windsurf	Supported	Windsurf supports Streamable HTTP servers and servers without authentication or bearer-token headers.
Gemini CLI	Supported	Gemini CLI supports Streamable HTTP servers and servers without authentication or bearer-token headers.
MCP SDK	Supported	MCP SDK supports Streamable HTTP servers and servers without authentication or bearer-token headers.

Computed from this server's validated transport, protocol and authentication against documented client support. Checks the catalog has not observed are not counted.

Similar servers

Exa — Exa web search and page-fetching tools for retrieving current web content. Works without an API key on a free tier; signing in raises limits. No authentication
Tavily — Tavily search, extract, crawl, and map tools for real-time web research. Clients sign in with OAuth, or append a Tavily API key as the tavilyApiKey query parameter. OAuth 2.1
Firecrawl — Firecrawl scrape, crawl, map, search, and structured-extraction tools that turn websites into LLM-ready Markdown or JSON. This endpoint signs in with OAuth; API-key clients use the /v2/mcp endpoint with a bearer token. OAuth 2.1
Grep by Vercel — Searches code across about a million public GitHub repositories by literal string or regular expression, with language, repository, and path filters. No authentication is required. No authentication
Parallel Search — Searches the web and fetches pages as compact markdown through Parallel's Search and Extract APIs. Works anonymously on a free tier; a Parallel API key as a bearer token raises the limits. No authentication
Parallel Task — Starts asynchronous Parallel deep-research and enrichment tasks, polls their status, and returns results as markdown. Supports OAuth or a Parallel API key as a bearer token. OAuth 2.1

Guides for this server

Watch this server for breaking changes

Share and embed

Maintain Jina AI? Embed this badge in your README. It follows the latest catalog validation result and links to this server profile.

Markdown

[![Tested on mcptest.io](https://mcptest.io/badge/server/jina.svg)](https://mcptest.io/servers/jina/)

HTML

<a href="https://mcptest.io/servers/jina/"><img src="https://mcptest.io/badge/server/jina.svg" alt="Tested on mcptest.io"></a>

reStructuredText

.. image:: https://mcptest.io/badge/server/jina.svg
   :alt: Tested on mcptest.io
   :target: https://mcptest.io/servers/jina/

Latest validation evidence

Validation status: Online when last tested
Validation checked at: Oct 26, 2026 at 11:06 AM
Validation detail: Negotiated stateful MCP 2025-11-25 at https://mcp.jina.ai/v1; detected transport streamable-http; authentication none

Tool inventory

What the catalog validator observed on Oct 26, 2026 at https://mcp.jina.ai/v1 without credentials. The live server may have changed since; connect in the Playground for the current list.

Tools provided by Jina AI 12

capture_screenshot_urlNo outputSchema
Screenshot a page as base64 JPEG. Use when the page must be seen rather than read.
Input firstScreenOnly?: boolean, return_url?: boolean, url: string
- firstScreenOnly?: booleanoptional
  Capture only the first screen instead of the full page. Faster.
- return_url?: booleanoptional
  Return URLs instead of base64 images.
- url: stringrequired
deduplicate_stringsNo outputSchema
Select the top-k semantically distinct strings from a list, dropping near-duplicates.
Input k?: integer, strings: array
- k?: integeroptional
  How many to keep. Omit to pick k automatically from diminishing returns.
- strings: arrayrequired
  Strings to deduplicate, up to 1000.
extract_pdfNo outputSchema
Extract figures, tables and equations from a PDF as images, by arXiv id or URL.
Input id?: string, max_edge?: number, type?: string, url?: string
- id?: stringoptional
  arXiv id, e.g. '2301.12345'. Give id or url.
- max_edge?: numberoptional
  Longest image edge in pixels, default 1024.
- type?: stringoptional
  Comma-separated types to keep: figure, table, equation. Default all.
- url?: stringoptional
  PDF URL. Give id or url.
guess_datetime_urlNo outputSchema
Guess when a page was published or last updated, with a confidence score. Checks HTTP headers, metadata, Schema.org, visible dates, feeds and sitemaps.
Input url: string
- url: stringrequired
primerNo outputSchema
Current time, user location and network environment for the session. Use before answering anything time- or location-dependent.
Input No parameters
read_urlNo outputSchema
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.
Input chunk_size?: integer, ocr?: boolean, page?: integer, question?: string, topk?: integer, url: any, withAllImages?: boolean, withAllLinks?: boolean
- chunk_size?: integeroptional
  Passage size in words, default 100. Larger gives more surrounding context, smaller pinpoints the answer. Comparable across scripts. Needs `question`.
- ocr?: booleanoptional
  Read 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?: integeroptional
  Which page the OCR pass should parse, 1-based. Needs `ocr`; the HTML path returns the whole document at once.
- question?: stringoptional
  Return only the passages answering this question, instead of the full body. Omit for the whole page.
- topk?: integeroptional
  Passages to return, default 1. Needs `question`.
- url: anyrequired
  Page or PDF URL, or up to 5 URLs to read in parallel.
- withAllImages?: booleanoptional
  Also return every image on the page.
- withAllLinks?: booleanoptional
  Also return every link on the page.
search_arxivNo outputSchema
Search arXiv preprints (physics, maths, CS, quantitative biology and finance).
Input num?: integer, query: any, tbs?: string
- num?: integeroptional
- query: anyrequired
- tbs?: stringoptional
  Age limit: qdr:h, qdr:d, qdr:w, qdr:m, qdr:y (hour to year).
search_imagesNo outputSchema
Search the web for images. Returns base64 JPEGs by default.
Input gl?: string, hl?: string, location?: string, num?: integer, query: string, return_url?: boolean, tbs?: string
- gl?: stringoptional
  Country code, e.g. 'de'.
- hl?: stringoptional
  Language code, e.g. 'zh-cn'.
- location?: stringoptional
- num?: integeroptional
- query: stringrequired
- return_url?: booleanoptional
  Return URLs and metadata instead of base64 images.
- tbs?: stringoptional
  Age limit: qdr:h, qdr:d, qdr:w, qdr:m, qdr:y (hour to year).
search_jina_blogNo outputSchema
Search Jina AI's news and blog at jina.ai/news: product announcements, model releases, technical write-ups.
Input num?: integer, query: any, tbs?: string
- num?: integeroptional
- query: anyrequired
- tbs?: stringoptional
  Age limit: qdr:h, qdr:d, qdr:w, qdr:m, qdr:y (hour to year).
search_ssrnNo outputSchema
Search SSRN working papers (social science, economics, law, finance, management).
Input num?: integer, query: any, tbs?: string
- num?: integeroptional
- query: anyrequired
- tbs?: stringoptional
  Age limit: qdr:h, qdr:d, qdr:w, qdr:m, qdr:y (hour to year).
search_webNo outputSchema
Search the web. Returns titles, URLs and search-engine snippets.
Input gl?: string, hl?: string, location?: string, num?: integer, query: any, tbs?: string
- gl?: stringoptional
  Country code, e.g. 'de'.
- hl?: stringoptional
  Language code, e.g. 'zh-cn'.
- location?: stringoptional
- num?: integeroptional
- query: anyrequired
- tbs?: stringoptional
  Age limit: qdr:h, qdr:d, qdr:w, qdr:m, qdr:y (hour to year).
sort_by_relevanceNo outputSchema
Rerank documents by relevance to a query, using Jina Reranker.
Input documents: array, query: string, top_n?: integer
- documents: arrayrequired
  Documents to rank, up to 1024.
- query: stringrequired
- top_n?: integeroptional