How to Use the Jina AI MCP in Mastra AI

Q: How do I register Jina AI tools inside a Mastra AI agent?

Instantiate the MCP client with the Vinkius URL, then call listTools to get the schemas. You can then spread these tools directly into your Mastra AI Agent definition.

Q: Can I require manual approval before Mastra AI uses Jina AI tools on this MCP server?

Yes. You can configure requireToolApproval on your Mastra AI agent specifically for the readurl or searchweb tools to prevent unauthorized web scraping.

Build resilient web-searching agents with Mastra AI and Jina AI.

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 MCP to Mastra AI

Create your Vinkius account to connect Jina AI 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 with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resilient web searching in Mastra AI

Workflows fail when external websites go down. By linking `search_web` with Mastra AI, you can configure automatic retries with exponential backoff so your Jina AI agent doesn't crash on a transient network error. If a target site blocks your request, the Mastra AI agent can try alternative paths or fall back to `check_fact` to verify the information from other sources without stopping the workflow. This prevents your Mastra AI pipeline from breaking midway.

Conditional branching for content ingestion

Mastra AI lets you build complex multi-step pipelines that adapt on the fly. You can use `read_url` to scrape a page, check the length with `tokenize_text`, and branch your Mastra AI logic based on the size. If the text is too long, the Mastra AI workflow routes it to `rerank_documents` to extract the most important parts before sending it to your LLM. This keeps your Mastra AI operational costs in check.

Verify statements automatically in your workflows

Running autonomous agents means you need guardrails. This MCP Server exposes `check_fact` directly to your Mastra AI agents, allowing them to audit claims before writing them to a database. You can set up a human-in-the-loop approval step in Mastra AI if the confidence score returned by the Jina AI fact-checker falls below your threshold. Doing this ensures your Mastra AI production data remains clean.

Setup guide

Set up Jina AI 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 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-mcp-client",
  servers: {
    "jina-ai-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Jina AI 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 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 MCP in Mastra AI

Instantiate the MCP client with the Vinkius URL, then call `listTools` to get the schemas. You can then spread these tools directly into your Mastra AI Agent definition.

Yes. You can configure `requireToolApproval` on your Mastra AI agent specifically for the `read_url` or `search_web` tools to prevent unauthorized web scraping.

Mastra AI's built-in workflow engine catches connection issues or API limits. If `get_embeddings` fails, the framework automatically retries the call using your configured backoff strategy.

Yes. The client automatically detects whether the hosted server uses Streamable HTTP or Server-Sent Events (SSE), keeping your connection stable during long-running workflows.

Your scraped URLs and search queries are processed inside an isolated, zero-trust V8 sandbox. Vinkius handles the MCP authentication securely, ensuring your raw text chunks are never exposed to external logs.

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