How do I use Jina AI with Claude?

You connect the MCP to your Claude client through Vinkius. Once connected, you can ask Claude to search the web or read URLs using the Jina capabilities.

Do I need to write code to use these capabilities?

No. This MCP allows you to trigger embeddings, searches, and text segmentation through natural language in your AI client.

What makes the web search different from a standard search?

The search returns context-rich, structured results that are specifically optimized for RAG and AI analysis rather than just a list of links.

Can this MCP help with RAG pipelines?

Yes. It includes capabilities for semantic segmentation, generating embeddings, and reranking documents to improve retrieval accuracy.

Is my data handled by Vinkius?

Vinkius hosts the MCP and manages the connection, but the actual processing is performed via your Jina AI account using your API key.

How can Jina AI help my agent provide more accurate answers?

Use the read_url_content capability to give your agent access to live web data. By converting URLs into clean Markdown, your agent can 'read' the latest information from documentation or news sites, grounding its answers in up-to-date facts.

What is the difference between search and rerank?

Search (embeddings) helps you find a broad set of relevant documents quickly. Rerank takes that smaller set and uses a more powerful cross-encoder model to sort them by exact semantic matching, ensuring the absolute best context is sent to the LLM.

Can I search the web through my agent using Jina?

Absolutely. Use the search_web_jina capability to dispatch a semantic query. Your agent will return structured results including snippets and titles from top web pages, allowing it to synthesize answers from the live internet.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Jina AI Search Foundation LLM Grounding to your AI

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Give your AI agent real-time web intelligence and precise data.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 6 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 6 available through Jina AI.

01
Generate embeddings
This capability creates vector embeddings from a list of strings. It uses Jina's models to power your semantic search and similarity workflows.
02
Rerank documents
This capability reranks search documents against a specific query. It improves relevance by re-ordering candidates based on semantic match.
03
Read URL content
This capability reads and extracts clean text from a URL. It's designed to strip away web noise so your agent gets pure Markdown context.

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through Jina AI.

04
Search web jina
This capability performs semantic web searches. It returns structured, context-rich results that are optimized for AI analysis and RAG.
05
Classify texts
This capability performs zero-shot text classification. It categorizes your input text against custom labels without needing manual model training.
06
Segment content
This capability handles semantic segmentation. It breaks long documents into cohesive chunks to make them ready for RAG retrieval.

Real work

What teams actually run

RAG Optimization

Use semantic segmentation and reranking to make your retrieval-augmented generation more accurate.

Real-time Research

Give your agent the ability to search the live web and read specific pages for up-to-date information.

Data Pipeline Automation

Automate the process of classifying text and extracting clean data from various web sources.

Semantic Search Workflows

Build custom search capabilities by generating embeddings and performing semantic queries.

Automate a task

Put Jina AI to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Jina AI works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Jina AI to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

825ms average. Fast in production.

Jina AI is checked daily against the live service.

Daily averagePeak 1169ms

Oct 7Today

Fastest day: 650ms
Slowest day: 1169ms
14-day trend: Improving-10%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 6 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Jina AI, so you can see the experience inside your AI.

It does not authenticate your account with Jina AI. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Jina AI Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_wGxcPgjZXIdTEE0fANy2lSVGB9dv2CeDi7TDmWBG/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Jina AI capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "jina-ai-search-foundation-llm-grounding-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_wGxcPgjZXIdTEE0fANy2lSVGB9dv2CeDi7TDmWBG/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Jina AI in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Jina AI owners hand off.

This MCP is built for technical users who need to bridge the gap between LLMs and real-world web data.

01
AI and RAG Developers
They hand off the task of real-time web access and precise document retrieval to their agents.
02
Data Scientists
They use the MCP to test embedding models and reranking logic without writing Python scripts.
03
Automation Engineers
They automate the extraction of clean web content and semantic classification for data pipelines.

FAQ

Questions Jina AI owners ask.

01
How do I use Jina AI with Claude?
You connect the MCP to your Claude client through Vinkius. Once connected, you can ask Claude to search the web or read URLs using the Jina capabilities.
02
Do I need to write code to use these capabilities?
No. This MCP allows you to trigger embeddings, searches, and text segmentation through natural language in your AI client.
03
What makes the web search different from a standard search?
The search returns context-rich, structured results that are specifically optimized for RAG and AI analysis rather than just a list of links.
04
Can this MCP help with RAG pipelines?
Yes. It includes capabilities for semantic segmentation, generating embeddings, and reranking documents to improve retrieval accuracy.
05
Is my data handled by Vinkius?
Vinkius hosts the MCP and manages the connection, but the actual processing is performed via your Jina AI account using your API key.
06
How can Jina AI help my agent provide more accurate answers?
Use the read_url_content capability to give your agent access to live web data. By converting URLs into clean Markdown, your agent can 'read' the latest information from documentation or news sites, grounding its answers in up-to-date facts.
07
What is the difference between search and rerank?
Search (embeddings) helps you find a broad set of relevant documents quickly. Rerank takes that smaller set and uses a more powerful cross-encoder model to sort them by exact semantic matching, ensuring the absolute best context is sent to the LLM.
08
Can I search the web through my agent using Jina?
Absolutely. Use the search_web_jina capability to dispatch a semantic query. Your agent will return structured results including snippets and titles from top web pages, allowing it to synthesize answers from the live internet.

Explore

More in AI Frontier

Connect Jina AI to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-03

Generate embeddings

Rerank documents

Read URL content

04-06

Search web jina

Classify texts

Segment content

What teams actually run

RAG Optimization

Real-time Research

Data Pipeline Automation

Semantic Search Workflows

Building your own app? The connector is yours to use.

Jina AI Connector

Claude Desktop

AI and RAG Developers

Data Scientists

Automation Engineers

How do I use Jina AI with Claude?

Do I need to write code to use these capabilities?

What makes the web search different from a standard search?

Can this MCP help with RAG pipelines?

Is my data handled by Vinkius?

How can Jina AI help my agent provide more accurate answers?

What is the difference between search and rerank?

Can I search the web through my agent using Jina?

Linkup (AI Search & RAG) AI Connector

Import.io (Web Data Extraction) AI Connector

LlamaIndex (AI Data Framework & RAG) AI Connector

Bing Search AI Connector

Suggestions

Web Scraper AI Connector

GroundX AI Connector

Data Pipeline Prover AI Connector

Lucidworks Fusion (AI Search & Discovery) AI Connector