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

Q: How does Jina AI (Search Foundation & LLM Grounding) help Cursor write better code?

It gives your Cursor agent live access to the web via searchwebjina and clean page extraction via readurlcontent. This stops the editor from writing code based on deprecated APIs, since it can read the latest documentation on the fly.

Q: How do I add the Jina AI (Search Foundation & LLM Grounding) MCP Server to my Cursor project?

You create a .cursor/mcp.json file in your project root and add the server details under the mcpServers key. Once saved, Cursor detects the MCP Server configuration, allowing the editor's AI to invoke the search and embedding tools immediately.

Q: How does the chunking tool handle large source code files?

The segmentcontent tool splits code or documentation into logical, semantic parts based on structure rather than arbitrary character counts. This preserves the context of functions and classes, making it easier for Cursor to analyze the code.

Feed clean web data and semantic search results directly into your active codebase using the Jina AI MCP Server in Cursor.

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 Cursor

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inject live documentation into Cursor Agent

This MCP Server tool `read_url_content` pulls live API documentation or GitHub readmes directly into your Cursor editor as clean markdown. Cursor uses this raw text to write code against the latest library versions instead of relying on outdated training data. When you don't know the exact URL of a library update, `search_web_jina` runs a semantic search to help Cursor locate the correct documentation. Your Cursor agent executes the search, grabs the top link, and reads it without you leaving your editor.

Optimize code search inside the Cursor editor

`rerank_documents` evaluates code snippets or documentation pages against your active Cursor programming task to find the best match. This ensures Cursor Agent prioritizes the correct helper functions when generating your code. To make this search efficient, `segment_content` breaks down massive codebases into logical chunks so Cursor doesn't hit context limits. You avoid hitting token limits because Cursor only reads the specific sections relevant to your current file.

Build vector search pipelines inside Cursor

`generate_embeddings` turns your local code files or text blocks into vector representations directly from the Cursor chat window. You can immediately use these vectors to test local search algorithms or update your database indexes. If you need to sort incoming logs, `classify_texts` runs zero-shot classification on raw strings to help Cursor route data. Cursor uses these classification outputs to write conditional logic and route data based on real-time API responses.

Setup guide

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

Prerequisites

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

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

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

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Jina AI (Search Foundation & LLM Grounding) transactions." If the MCP tools are loaded correctly, Cursor will call the Jina AI (Search Foundation & LLM Grounding) tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

It gives your Cursor agent live access to the web via `search_web_jina` and clean page extraction via `read_url_content`. This stops the editor from writing code based on deprecated APIs, since it can read the latest documentation on the fly.

Yes, the server tools are fully accessible to Cursor's Agent mode. When you ask the agent to fix a bug or implement a new API, it can automatically call these tools to search the web and read documentation.

You create a `.cursor/mcp.json` file in your project root and add the server details under the `mcpServers` key. Once saved, Cursor detects the MCP Server configuration, allowing the editor's AI to invoke the search and embedding tools immediately.

The `segment_content` tool splits code or documentation into logical, semantic parts based on structure rather than arbitrary character counts. This preserves the context of functions and classes, making it easier for Cursor to analyze the code.

All code snippets and search queries sent through the MCP Server are encrypted in transit and processed on Jina's secure infrastructure. No data is saved or used to train models, and Vinkius runs the server in an ephemeral sandbox to block persistent access.

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