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

Let Cascade autonomously search the live web, scrape clean markdown, and build vectors directly inside Windsurf.

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 Windsurf

Create your Vinkius account to connect Jina AI (Search Foundation & LLM Grounding) to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Web Grounding for Windsurf Cascade

`search_web_jina` gives your AI client immediate access to the live web without leaving your workspace. Cascade takes your high-level goal, runs the semantic search tool, and grabs the exact URLs it needs. It does this in one continuous chain without waiting for your approval at every step. Once it has the links, Cascade uses `read_url_content` to pull down clean, markdown-formatted text from those pages. This strips out the junk like ads and navigation menus, leaving only the raw data your agent needs to write accurate code or documentation.

Deep Document Reranking in Your IDE

`rerank_documents` lets you sort through massive piles of text to find the exact pieces that match your query. You don't have to rely on simple keyword matching that misses the actual context of your codebase or documentation. This MCP Server tool takes a list of text chunks and scores them based on actual semantic relevance. Cascade uses these scores to filter out the noise, ensuring that only the most relevant snippets feed into your context window.

Vector Generation and Text Chunking

`segment_content` breaks down massive text files into clean, logical semantic chunks before you feed them to an embedding model. Instead of arbitrary character limits, this tool slices your files where the actual meaning changes. After chunking, `generate_embeddings` converts those text segments into vector arrays. Cascade can run this entire pipeline to index your local docs, while `classify_texts` categorizes the files automatically to keep your workspace organized.

Setup guide

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

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Jina AI (Search Foundation & LLM Grounding) payment history." If connected, Cascade will call the Jina AI (Search Foundation & LLM Grounding) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "jina-ai-search-foundation-llm-grounding-mcp": {
      "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 Windsurf

Cascade chains these tools together to execute multi-step research tasks. When you ask it to update an API, it searches with `search_web_jina`, scrapes the docs with `read_url_content`, and updates your files in one go.

Yes. You can have Cascade read your local documentation files, run `segment_content` to split them logically, and then call `generate_embeddings` to get vector representations.

You need a Jina API key to run these tools. Add the key to your environment variables or directly inside your Windsurf MCP configuration file to authenticate.

Standard keyword search often brings back irrelevant code files. Running `rerank_documents` ensures Cascade only reads the files that actually solve your problem, saving context window space.

Your search queries and scraped web content travel securely to Jina's endpoints for processing. Vinkius runs this MCP Server in an isolated sandbox, meaning your raw text data is never stored locally on our servers or used for model training.

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