How to Use the Jina AI (Search Foundation & LLM Grounding) MCP in Claude Code

Q: How do I add the Jina AI (Search Foundation & LLM Grounding) server to Claude Code?

Run the add command in your terminal: claude mcp add --transport http jina-search -- . Make sure to pass your API key as a header flag during setup.

Pipe clean web search, semantic text chunking, and vectors directly into Claude Code for headless shell automation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Jina AI (Search Foundation & LLM Grounding) MCP to Claude Code

Create your Vinkius account to connect Jina AI (Search Foundation & LLM Grounding) to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Jina AI (Search Foundation & LLM Grounding) with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless Web Searching and Scraping

`search_web_jina` turns your terminal into a semantic search engine that Claude Code can query programmatically. You can pipe search results directly into other shell commands or use them to feed deployment scripts. When you need to inspect a specific page, `read_url_content` pulls down clean markdown text straight to your terminal. This allows your agent to extract configuration steps or API keys from online docs without opening a browser.

Command-Line Vector Generation via MCP Server

`generate_embeddings` converts raw text arrays into high-dimensional vector embeddings directly from your command line. Your agent can run this tool to process local files during CI/CD steps or automated database migrations. To make sure those vectors are accurate, `segment_content` slices your text into logical chunks first. This prevents vector distortion that happens when you try to embed too much unrelated text at once.

CLI-Driven Document Reranking

`rerank_documents` allows you to sort through thousands of log lines or documentation files by relevance to a specific incident. This tool is perfect for SREs who need to find the root cause of a system failure quickly. You can also run `classify_texts` to instantly tag incoming server logs or error reports. Claude Code uses these classifications to route tasks, trigger alerts, or commit targeted hotfixes to your repository.

Setup guide

Set up Jina AI (Search Foundation & LLM Grounding) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see jina-ai-search-foundation-llm-grounding-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Jina AI (Search Foundation & LLM Grounding) transactions." It will automatically discover and invoke the available Jina AI (Search Foundation & LLM Grounding) tools.

Terminal

claude mcp add --transport http jina-ai-search-foundation-llm-grounding-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Jina AI (Search Foundation & LLM Grounding) MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "jina-ai-search-foundation-llm-grounding-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Jina AI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Jina AI (Search Foundation & LLM Grounding) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Jina AI (Search Foundation & LLM Grounding) MCP in Claude Code

Run the add command in your terminal: `claude mcp add --transport http jina-search -- `. Make sure to pass your API key as a header flag during setup.

Yes. Because this is an MCP Server for a terminal-based client, you can automate tasks like documentation generation or web-grounded testing directly in your GitHub Actions or custom scripts.

Standard grep searches miss semantic context. This tool ranks log lines based on what they actually mean, letting Claude Code find silent failures that don't match specific error keywords.

The tool expects a JSON array of strings. You can pass raw text files or piped shell output, and the server will return the raw vector arrays.

All code fragments, logs, and URLs are processed in memory within our secure V8 Isolate Sandbox. The text is sent directly to Jina via encrypted channels, and no data is ever written to persistent storage or used to train models.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript