Jina AI Connector for AI agents.
6 live capabilities
Get grounded web intelligence and clean content extraction for your RAG pipelines.
Waiting for input…
Why people use Jina AI
Jina AI for RAG Pipeline Data Extraction
This Connector handles the extraction for you. Your agent pulls the clean content directly, meaning it gets exactly what it needs to answer your question without the extra noise.
What Vinkius changes
Your agent gets clean, usable web data instead of raw HTML.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Fact-checking a news summary
An editor asks the agent to verify a summary.
- Real-world use case 02
Building a RAG pipeline
A developer uses read_url to scrape documentation and rerank_documents to prioritize the most relevant pages for the agent.
- Real-world use case 03
Semantic search audit
A data scientist uses get_embeddings to see how well different queries map to their internal data for a similarity audit.
Complete set · 6capabilities
The complete Jina AI capability set.
These are the exact actions your AI can choose when you ask it to work with Jina AI.
01—03
3 capabilities in this set.
Part of 6 available through Jina AI.
- 01 Capability
Get embeddings
Convert a list of strings into vector embeddings. Use this for custom similarity audits and semantic search.
- 02 Capability
Read url
Pull cleaned, LLM-ready content from a specific website. It removes the junk so your agent sees only the text.
- 03 Capability
Rerank documents
Sort a list of documents to find the best matches for a query. This prioritizes the most relevant info.
04—06
3 capabilities in this set.
Part of 6 available through Jina AI.
- 04 Capability
Search web
Perform a web search specifically designed for AI consumption. It returns snippets curated for your agent.
- 05 Capability
Tokenize text
Break down text into tokens for accurate LLM processing. This ensures your agent handles data exactly as expected.
- 06 Capability
Check fact
Verify if a statement is true based on current web data. This helps your agent avoid making false claims.
Set up in minutes
One URL. Then ask Jina AI to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Jina AI 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_Gza6Drx72jH8vtBy0iAFsasyQnT7I8NYxoBnHuHb/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, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Jina AI for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_Gza6Drx72jH8vtBy0iAFsasyQnT7I8NYxoBnHuHb/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 URL.
- Step 03
Save and start
Save the connection and enable Jina AI in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"jina-ai": {
"url": "https://edge.vinkius.com/vk_preview_Gza6Drx72jH8vtBy0iAFsasyQnT7I8NYxoBnHuHb/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
Open Agent mode in chat and ask: "Using Jina AI, help me...". 6 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"jina-ai": {
"url": "https://edge.vinkius.com/vk_preview_Gza6Drx72jH8vtBy0iAFsasyQnT7I8NYxoBnHuHb/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
Ask Copilot: "Using Jina AI, help me...". 6 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"jina-ai": {
"url": "https://edge.vinkius.com/vk_preview_Gza6Drx72jH8vtBy0iAFsasyQnT7I8NYxoBnHuHb/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
Open Cascade and ask: "Using Jina AI, help me...". 6 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"jina-ai": {
"url": "https://edge.vinkius.com/vk_preview_Gza6Drx72jH8vtBy0iAFsasyQnT7I8NYxoBnHuHb/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
Ask Cline: "Using Jina AI, help me...". 6 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add jina-ai --transport http "https://edge.vinkius.com/vk_preview_Gza6Drx72jH8vtBy0iAFsasyQnT7I8NYxoBnHuHb/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
Ask Claude: "Using Jina AI, show me...". 6 tools are ready
Where the request belongs
Work Jina AI can move forward.
This is for the engineer who is tired of cleaning messy scraped data and the researcher who needs grounded facts without the noise of standard search results.
Knowledge Engineer
Auditing RAG pipelines and ensuring the content pulled from URLs is actually clean and relevant.
AI Researcher
Monitoring search contexts and optimizing how an agent retrieves information from the live web.
Data Scientist
Performing rapid audits of semantic embeddings and reranking scores for search accuracy.
Operations Lead
Automating web intelligence queries to manage research tasks across different teams.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsTavily
Search the web for AI. audit search context, answers, and extracted content via AI.
Exa AI
Search the web with neural embeddings that understand meaning, not just keywords, and return the most relevant results for any query.
Exa
Find exactly the web content you need with semantic search that understands context and returns high-quality curated results.
SerpApi
Equip your AI agent with real-time web search capabilities across Google, Bing, Baidu, Yahoo, and DuckDuckGo.
Jina AI (Search Foundation & LLM Grounding)
Power your RAG and search via Jina AI. generate embeddings, rerank documents, read URLs, and perform semantic web search.
ValueSERP
Bring real-time Google Search data into your AI agent. Search organically, find images, news, scholars, and related questions without getting blocked.
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.
How does Jina AI help my AI agent read websites?
Jina AI acts as a filter that strips away ads, headers, and navigation menus. Your agent receives only the clean, core text from a URL, which saves context space and improves accuracy.
Can I use Jina AI to check if my agent is hallucinating?
Yes. By using the fact-checking capabilities, your agent can verify its own statements or your queries against real-time web data to ensure everything it says is grounded in reality.
Is Jina AI good for building a RAG system?
It is ideal for RAG. It provides the capabilities to extract clean data from the web and rerank those results so your agent always prioritizes the most relevant information for the user.
How does Jina AI handle search results for LLMs?
It provides search results specifically curated for machine consumption. This means the snippets are optimized for your agent to read and process quickly without the noise of standard search engines.
Can Jina AI help me rank my search results?
Yes. It includes a capability to rerank documents based on a query. This allows your agent to sort a list of results and focus on the best matches first, improving the quality of the final answer.
Does Jina AI clean up website content automatically?
Yes. When your agent uses the reader capability, the Connector automatically handles the extraction and cleaning. You get structured data instead of raw HTML.
How do I find my Jina AI API Key?
Log in to your Jina AI dashboard, and you will find your API Key on the main page. Copy and paste it below.
What is the difference between Jina Search and Reader?
Jina Search searches across the entire web for results, while Reader extracts the specific main content from a single provided URL, optimized for AI models.
Can the agent rerank my search results?
Yes. The rerank_documents capability allows your agent to sort a list of documents by relevancy to a query using Jina's advanced reranking models.
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