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

Q: How does this MCP Server secure the URLs and text my Mastra agents process?

All URL strings and text payloads processed by readurlcontent or generateembeddings travel through encrypted TLS channels to the MCP server. The Vinkius sandbox isolates the execution environment so that no external processes can intercept your agent's data. Your target URLs and scraped content are never cached or stored on the host.

Build resilient web-searching agents with Mastra AI and this grounding 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 Mastra AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resilient web search workflows in Mastra AI

The `search_web_jina` tool executes semantic web queries to retrieve structured data for your Mastra AI agents. When a search fails due to network hiccups, Mastra's built-in workflow engine triggers automatic retries with exponential backoff. This setup ensures your autonomous search pipelines do not break mid-run. You define the search step in your workflow, and Mastra manages the execution, handling errors gracefully without manual intervention.

Multi-step document ingestion and reranking

The `segment_content` and `rerank_documents` tools divide long text into logical paragraphs and rank them by relevance to a query. In a Mastra AI workflow, you can pipe raw scraped text from a URL directly into these tools to filter out noise. This conditional pipeline ensures your agents only work with high-quality data. If the relevance score from the reranker falls below your threshold, Mastra can branch the workflow to alert an admin or try a different search query.

Zero-shot classification for agent routing

The `classify_texts` tool categorizes input text into your defined labels without prior training. Mastra AI uses these classification outputs to determine which branch of a workflow to execute next. For example, incoming web content can be classified as spam, news, or transactional. Your agent then routes the clean text to the correct database or processing queue based on that classification.

Setup guide

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

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Jina AI (Search Foundation & LLM Grounding) tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "jina-ai-search-foundation-llm-grounding-mcp-client",
  servers: {
    "jina-ai-search-foundation-llm-grounding-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Jina AI (Search Foundation & LLM Grounding) Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Jina AI (Search Foundation & LLM Grounding) tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Jina AI (Search Foundation & LLM Grounding) transactions"
);
console.log(result.text);

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 Mastra AI

You import the client from the Mastra SDK and register the Vinkius MCP server URL. Once connected, you can spread the server tools directly into your agent's tool list. This allows your workflows to call search and classification steps natively.

Yes, you can configure Mastra's human-in-the-loop feature for sensitive tools like `search_web_jina` or `read_url_content`. The workflow pauses and waits for an admin signature before executing the web request. This prevents your agents from accessing unvetted external sites.

Mastra AI manages rate limits using its built-in retry mechanisms and exponential backoff configuration. If the `generate_embeddings` tool hits a rate limit, the workflow pauses and retries automatically. This ensures your background data-ingestion pipelines remain stable.

You deploy your Mastra project to your cloud provider using the standard Mastra CLI commands. The connection to the MCP server is maintained securely via your Vinkius endpoint token. Your deployed agents can access the search and scraping tools instantly without extra configuration.

All URL strings and text payloads processed by `read_url_content` or `generate_embeddings` travel through encrypted TLS channels to the MCP server. The Vinkius sandbox isolates the execution environment so that no external processes can intercept your agent's data. Your target URLs and scraped content are never cached or stored on the host.

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