How to Use the Linkup (AI Search & RAG) MCP in Pydantic AI

Bring strict type safety to your RAG pipelines with Pydantic AI and real-time web search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Linkup (AI Search & RAG) MCP to Pydantic AI

Create your Vinkius account to connect Linkup (AI Search & RAG) 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 Linkup (AI Search & RAG) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe web search for Pydantic AI agents

Stop letting malformed web data crash your production agents. This MCP Server ensures that all responses from `search_web` fit your strict Python type definitions before your agent processes it. If a search result returns an unexpected schema, Pydantic AI raises a validation error immediately. You get complete runtime safety, preventing silent failures and keeping your data pipelines clean.

Model-agnostic web scraping with hard validation

Local models and commercial APIs both need reliable web inputs to function. When your agent calls `fetch_url`, the raw page text is parsed into structured data that matches your target model's schema. This removes the guesswork from web scraping. Your agent gets clean, structured text that is guaranteed to match your validation layers, regardless of which LLM is running under the hood.

Unified toolset configuration for external servers

Running `search_web` across multiple environments shouldn't require complex MCP Server connection logic. By using the unified MCP Server toolset constructor, you can point your agent to the external Vinkius server with a single connection string. This replaces deprecated HTTP adapters and simplifies your codebase. Your Pydantic AI agent connects over SSE or Streamable HTTP, giving you a stable, production-ready connection in two lines of code.

Setup guide

Set up Linkup (AI Search & RAG) 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": {
        "linkup-ai-search-rag-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Linkup (AI Search & RAG) 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 Linkup. 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 Linkup (AI Search & RAG) 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 Linkup (AI Search & RAG) MCP in Pydantic AI

Use the unified MCP Server toolset class to connect to your Vinkius endpoint. Pass this toolset into the `toolsets` parameter when initializing your type-safe agent.

The framework will raise a validation error instantly. This prevents corrupted search results from polluting your agent's reasoning loop or causing silent downstream failures.

Yes, the integration is completely model-agnostic. You can run `search_web` to retrieve context and feed it to a local model while maintaining strict validation.

The unified toolset handles both SSE and Streamable HTTP transports automatically. It simplifies your imports and ensures compatibility with future framework updates.

Your search queries, target URLs, and API tokens are processed in zero-trust, ephemeral V8 sandbox environments. No data is stored on disk or used for training. Each connection is isolated, ensuring absolute security for your enterprise data pipelines.

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