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

Q: How do we share the Jina AI (Search Foundation & LLM Grounding) MCP Server configuration across our team in VS Code Copilot?

You create a .vscode/mcp.json file in your repository root and commit it to Git. When team members open the project in VS Code, Copilot automatically loads the server and makes the search tools available.

Q: How does Jina AI (Search Foundation & LLM Grounding) improve VS Code Copilot's code generation?

It provides clean, markdown-formatted web content via readurlcontent instead of messy HTML. This gives Copilot accurate context, resulting in fewer syntax errors and higher-quality code suggestions.

Q: Can we limit which web domains the search tool accesses?

The searchwebjina tool performs broad semantic searches, but you can instruct VS Code Copilot to focus its queries on specific documentation domains. This keeps the retrieved code context highly relevant to your tech stack.

Equip your engineering team with live web search and document reranking inside VS Code Copilot using this MCP Server.

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 VS Code Copilot

Create your Vinkius account to connect Jina AI (Search Foundation & LLM Grounding) to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground VS Code Copilot with live web search

`search_web_jina` gives your entire team the ability to query the web for live technical solutions directly inside VS Code Copilot. By committing the server configuration to your repository, every developer gets instant access to semantic web results. Once the search returns the right resource, `read_url_content` extracts the text of that page directly into your VS Code Copilot chat. Copilot uses the clean markdown to debug errors or write code based on real-time web documentation.

Manage large document context in VS Code Copilot

`segment_content` chunks long text files and documentation into logical, semantic pieces before passing them to VS Code Copilot. This prevents the editor from overflowing its context window when analyzing massive log files or API specs. To ensure Copilot focuses on the most critical data, `rerank_documents` scores and sorts these text chunks based on your active coding query. You get precise code completions because the most relevant technical details are placed at the top of the prompt.

Run text classification directly in VS Code

This MCP Server tool `classify_texts` lets you test categorization logic inside VS Code Copilot by running zero-shot classification on text arrays. Developers can prototype routing features and verify classification accuracy before writing any backend code. When building search features, `generate_embeddings` converts your text strings into vectors directly inside VS Code Copilot. This lets your team test vector search pipelines and inspect embedding outputs directly in their primary development environment.

Setup guide

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

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

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

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Jina AI (Search Foundation & LLM Grounding) tools listed. Try asking: "List my recent Jina AI (Search Foundation & LLM Grounding) transactions" and Copilot will invoke them automatically.

.vscode/mcp.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 VS Code Copilot

You create a `.vscode/mcp.json` file in your repository root and commit it to Git. When team members open the project in VS Code, Copilot automatically loads the server and makes the search tools available.

No, the search and embedding tools require an active internet connection to communicate with the Jina API. However, you can still use `segment_content` to chunk local files offline if the MCP Server is running locally on your machine.

It provides clean, markdown-formatted web content via `read_url_content` instead of messy HTML. This gives Copilot accurate context, resulting in fewer syntax errors and higher-quality code suggestions.

The `search_web_jina` tool performs broad semantic searches, but you can instruct VS Code Copilot to focus its queries on specific documentation domains. This keeps the retrieved code context highly relevant to your tech stack.

Your code fragments, text chunks, and search terms sent through this MCP Server are transmitted over secure HTTPS directly to Jina's API endpoints. The data is processed in memory to return search results or embeddings and is immediately discarded without being stored or used for 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