Jina AI (Search Foundation & LLM Grounding) Connector for AI agents.
6 live capabilities
Ground your workflow in real-time web data with semantic search.
Waiting for input…
Why people use Jina AI (Search Foundation & LLM Grounding)
Jina AI for RAG and Semantic Search
This Connector changes the game by handling the extraction for you. It pulls the core content from a URL and gives your agent clean Markdown. You get high-quality data ready for your RAG pipeline without the manual cleanup, so your agent actually finds the answers it needs.
What Vinkius changes
You get live, clean web data grounded in your agent's workflow.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Fixing hallucinations on old info
A user asks for the latest specs on a new product.
- Real-world use case 02
Summarizing messy blog posts
A user wants to summarize a specific blog post.
- Real-world use case 03
Improving RAG retrieval accuracy
A user asks a complex question about a legal doc.
Complete set · 6capabilities
The complete Jina AI (Search Foundation & LLM Grounding) capability set.
These are the exact actions your AI can choose when you ask it to work with Jina AI (Search Foundation & LLM Grounding).
01—03
3 capabilities in this set.
Part of 6 available through Jina AI (Search Foundation & LLM Grounding).
- 01 Capability
Classify texts
Assign labels to text inputs using zero-shot classification with confidence scores. Use this to categorize data without training a model.
- 02 Capability
Segment content
Split long documents into smaller, meaningful chunks that keep their original meaning intact. This optimizes your retrieval for vector storage.
- 03 Capability
Generate embeddings
Turn a list of text strings into vector embeddings for your database. This is essential for building semantic search systems.
04—06
3 capabilities in this set.
Part of 6 available through Jina AI (Search Foundation & LLM Grounding).
- 04 Capability
Rerank documents
Re-order a list of search results to put the most relevant ones at the top. This ensures your agent sees the best context first.
- 05 Capability
Read url content
Pull clean Markdown text from a website while stripping out the noise. It's the best way to feed live web pages to your agent.
- 06 Capability
Search web jina
Perform a semantic web search that returns structured results for RAG. It finds relevant information based on meaning, not just keywords.
Set up in minutes
One URL. Then ask Jina AI (Search Foundation & LLM Grounding) to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Jina AI (Search Foundation & LLM Grounding) from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_wGxcPgjZXIdTEE0fANy2lSVGB9dv2CeDi7TDmWBG/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Jina AI (Search Foundation & LLM Grounding), and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Jina AI (Search Foundation & LLM Grounding) for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_wGxcPgjZXIdTEE0fANy2lSVGB9dv2CeDi7TDmWBG/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Jina AI (Search Foundation & LLM Grounding) URL.
- Step 03
Save and start
Save the connection and enable Jina AI (Search Foundation & LLM Grounding) in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"jina-ai-search-foundation-llm-grounding": {
"url": "https://edge.vinkius.com/vk_preview_wGxcPgjZXIdTEE0fANy2lSVGB9dv2CeDi7TDmWBG/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Jina AI (Search Foundation & LLM Grounding)
Open Agent mode in chat and ask: "Using Jina AI (Search Foundation & LLM Grounding), help me...". 6 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"jina-ai-search-foundation-llm-grounding": {
"url": "https://edge.vinkius.com/vk_preview_wGxcPgjZXIdTEE0fANy2lSVGB9dv2CeDi7TDmWBG/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Jina AI (Search Foundation & LLM Grounding)
Ask Copilot: "Using Jina AI (Search Foundation & LLM Grounding), help me...". 6 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"jina-ai-search-foundation-llm-grounding": {
"url": "https://edge.vinkius.com/vk_preview_wGxcPgjZXIdTEE0fANy2lSVGB9dv2CeDi7TDmWBG/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Jina AI (Search Foundation & LLM Grounding)
Open Cascade and ask: "Using Jina AI (Search Foundation & LLM Grounding), help me...". 6 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"jina-ai-search-foundation-llm-grounding": {
"url": "https://edge.vinkius.com/vk_preview_wGxcPgjZXIdTEE0fANy2lSVGB9dv2CeDi7TDmWBG/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Jina AI (Search Foundation & LLM Grounding)
Ask Cline: "Using Jina AI (Search Foundation & LLM Grounding), help me...". 6 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add jina-ai-search-foundation-llm-grounding --transport http "https://edge.vinkius.com/vk_preview_wGxcPgjZXIdTEE0fANy2lSVGB9dv2CeDi7TDmWBG/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Jina AI (Search Foundation & LLM Grounding)
Ask Claude: "Using Jina AI (Search Foundation & LLM Grounding), show me...". 6 tools are ready
Where the request belongs
Work Jina AI can move forward.
The RAG developer who's tired of their agent hallucinating because the search results are garbage. It's for people building production-grade search.
RAG Engineer
Building production pipelines that need reliable grounding in live web data.
Data Scientist
Testing embedding models and reranking logic without writing custom Python scripts.
Automation Engineer
Scraping clean data from the web at scale for internal company databases.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsLinkup (AI Search & RAG)
Power your AI agents with real-time web search via Linkup. execute semantic queries and extract RAG-ready content.
Exa AI
Search the web with neural embeddings that understand meaning, not just keywords, and return the most relevant results for any query.
Jina AI
Search and read the web for AI. audit search results and reader content via AI.
Swiftype
Connect your AI to Elastic Swiftype. Query your search engines, manage documents, and retrieve deep analytical insights natively from the terminal.
GroundX
Data search and RAG optimization platform.
R2R
Equip your AI with direct access to your R2R engine. execute vector searches, run precise RAG queries, and manage your documents.
Bring your own AI
Change the model, client or framework. Keep Jina AI connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Jina AI.
The practical details behind the request, access and result.
What is Jina AI MCP for?
It helps your agent understand the live web and your own documents better. It handles the hard parts of search, like cleaning up web pages and ranking results so your agent doesn't get confused by irrelevant data.
How does Jina AI MCP help with RAG?
It provides a complete toolkit for Retrieval-Augmented Generation. You can turn URLs into clean text, create embeddings, and rerank your search results to make your RAG system much more accurate.
Can I use Jina AI MCP to scrape websites?
Yes, it's great for that. Instead of getting a mess of HTML, it pulls out the clean content from a URL so your agent can read it without getting distracted by ads or menus.
Does Jina AI MCP support semantic search?
It does. It goes beyond basic keywords to find results that actually match the meaning of your query, which is a huge upgrade for any search-heavy application.
How does Jina AI MCP handle long documents?
It has a capability to split long text into smaller, meaningful chunks. This makes it much easier for your agent to find specific information within large files like manuals or long reports.
Is Jina AI MCP good for data classification?
It's excellent for zero-shot classification. You can give your agent a list of categories and it will sort your data into those categories without you needing to train a custom model.
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.
One connection away
Give your agent a direct line to Jina AI.
Connect Jina AI once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available