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

Q: How do I set up Jina AI (Search Foundation & LLM Grounding) with Pydantic AI?

Install the slim package, then use the MCPToolset to connect to the server URL. Pass this as a toolset to your agent to get immediate access to all validated tools.

Strict type-safe search for Pydantic AI. Use Jina AI to ground your agents with validated data.

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 Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-validated search for Pydantic AI

Stop worrying about malformed API responses. Every tool output is validated against your Pydantic models at runtime, so your agent crashes before it can process garbage data. Use `search_web_jina` to get your results. If the data structure doesn't match your schema, the agent catches it immediately.

Grounding your agent with Pydantic AI

Feed live web data into your agent with confidence. The `read_url_content` tool pulls markdown that adheres to strict typing, ensuring your agent only works with data it can actually understand. This prevents the silent data corruption common in less rigid frameworks. You define the model, the server provides the data, and the agent executes.

Precise embedding control for Pydantic AI

Vectorize your content with `generate_embeddings` knowing exactly what the output format is. You get consistent arrays that fit your database schema every time. When handling complex text, `segment_content` ensures your chunks are correctly typed and ready for storage. It is the safest way to build a reliable RAG pipeline.

Setup guide

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

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "jina-ai-search-foundation-llm-grounding-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Jina AI (Search Foundation & LLM Grounding) tools.",
)

result = await agent.run("List recent Jina AI (Search Foundation & LLM Grounding) transactions")
print(result.output)

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 Pydantic AI

Install the slim package, then use the `MCPToolset` to connect to the server URL. Pass this as a toolset to your agent to get immediate access to all validated tools.

Yes. Because Pydantic AI validates every response, you can define a schema for your search results. If `search_web_jina` returns unexpected fields, the agent will throw a validation error.

It is. Since the toolset is independent of the underlying LLM, you can swap between models without changing how you interact with the Jina AI server.

The agent fails loudly. This prevents your system from continuing with bad data, which is critical if you are building production-ready agents.

The server performs all operations in a secure, ephemeral environment. It only touches your data during the request-response cycle, and no records are kept of the content being validated.

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