How to Use the Jina AI MCP in Pydantic AI

Q: How do I install the Jina AI toolset for Pydantic AI?

Run pip install "pydantic-ai-slimmcp" in your terminal. Then, initialize an MCPToolset pointing to your Vinkius HTTP URL and add it to your Agent's toolsets list.

Q: How does runtime validation work for these tools?

Every response from tools like searchweb or checkfact is validated against Pydantic models. If the server returns unexpected fields, the agent raises a validation error.

Connect Jina AI to your Pydantic AI agent for type-safe web search, markdown scraping, and document reranking.

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 Pydantic AI

Create your Vinkius account to connect Jina AI 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 with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe web scraping with MCP Server integration

Your agent calls `read_url` or `search_web` to fetch web data that is instantly validated against strict schemas at runtime. This avoids silent failures and malformed payloads in production. If a search result does not match the expected structure, the framework fails loudly. This guarantees your agent only processes structured, clean data from the MCP server.

Rerank and tokenize with absolute correctness

Your agent uses `rerank_documents` and `tokenize_text` to clean search results and fit them perfectly within model limits. This combination prevents out-of-memory errors and context truncation. You write the schema, and the framework ensures the MCP server outputs match it perfectly. No unexpected fields can slip past your validation layers.

Fact-check and embed data safely

Your agent uses `check_fact` to verify claims and `get_embeddings` to convert validated text into vectors. This ensures your vector database is never contaminated with false information. Every step is fully typed and validated by your Pydantic AI agent. You get clean, verified vectors without writing custom sanitization code.

Setup guide

Set up Jina AI 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-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 tools.",
)

result = await agent.run("List recent Jina AI 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 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 Pydantic AI

Run pip install "pydantic-ai-slim[mcp]" in your terminal. Then, initialize an MCPToolset pointing to your Vinkius HTTP URL and add it to your Agent's toolsets list.

Use the unified MCPToolset class, which supports both streamable HTTP and SSE transports. The older MCPServerHTTP class is deprecated.

Yes. The framework is model-agnostic, meaning you can use these search and scraping tools with Anthropic, Gemini, or even local models running on your machine.

Every response from tools like search_web or check_fact is validated against Pydantic models. If the server returns unexpected fields, the agent raises a validation error.

Every request is routed through a zero-trust V8 isolate sandbox. Your raw text tokens, target URLs, search queries, embeddings, and content are processed in-flight without any persistent disk storage or logging on the MCP server side.

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