How to Use the Raven Tools MCP in Pydantic AI

Q: How do I configure Raven Tools in Pydantic AI?

Install the slim library and use the MCPToolset. You pass the HTTP URL of your server and include it in the toolsets argument for your agent.

Use Raven Tools with Pydantic AI for type-safe SEO data retrieval and rigorous agent validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Raven Tools MCP to Pydantic AI

Create your Vinkius account to connect Raven Tools to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Raven Tools with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-safe rank tracking with Pydantic AI

Wrap `get_rank` calls in Pydantic models to ensure the data your agent receives is always correct. If the API returns malformed data, your agent stops immediately. This prevents silent errors in your reporting. You know exactly what data your agent is using to inform your SEO strategy.

Validate site audits using an MCP Server

Use `get_site_audit` to retrieve technical SEO data that must conform to your strict schema. Pydantic AI validates every field before your agent acts on the audit results. This approach stops hallucinations in their tracks. You only work with clean, verified data.

Manage keyword sets with Pydantic AI

Call `add_keyword` and `remove_keyword` through your agent using validated inputs. This ensures your keyword lists remain accurate and free of junk data. Your agent maintains the integrity of your campaigns. It follows your rules for what constitutes a valid keyword.

Setup guide

Set up Raven Tools 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": {
        "raven-tools-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Raven Tools tools.",
)

result = await agent.run("List recent Raven Tools 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 Raven Tools. 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 Raven Tools 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 Raven Tools MCP in Pydantic AI

Install the slim library and use the `MCPToolset`. You pass the HTTP URL of your server and include it in the toolsets argument for your agent.

Because Pydantic AI validates responses against your models, any unexpected API output triggers a validation error. It keeps your agent from processing bad data.

It is. Since the tools return structured data, you can define Pydantic models for every tool result. This makes your agent's logic predictable.

Your connection is ephemeral and handled via the Vinkius sandbox. Your site audit results are only visible to the agent you authorize.

You can. Pydantic AI is model-agnostic, meaning you can connect any local model to the MCP server for private SEO analysis.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python