How to Use the Mozscape MCP in Pydantic AI

Q: Can I build a reliable backlink checker with Mozscape and Pydantic AI?

Yes, it's the ideal use case. Your agent can use fetchlinkstatus, and Pydantic AI guarantees the response is a clean boolean. You'll never have to write defensive code to handle None or other unexpected return values.

Build type-safe SEO agents that won't fail silently, powered by Mozscape and Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mozscape MCP to Pydantic AI

Create your Vinkius account to connect Mozscape 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 Mozscape with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Guaranteed Data Integrity

This MCP Server is built for developers who hate bad data. When your agent calls `fetch_site_metrics`, Pydantic AI validates the response against a strict model. If the API ever returned a `null` for Domain Authority, your agent would raise a `ValidationError` instantly. There's no silent data corruption. You can trust the numbers your agent reports because every field from every tool call is checked, every single time.

Build Reliable, Model-Agnostic Agents

Write your SEO logic once. The Pydantic AI toolset for Mozscape works the same whether you're using GPT-4, Claude 3, or a local model. You can swap the underlying LLM without rewriting how your agent calls `v2_url_metrics` or `list_linking_domains`. This frees you from vendor lock-in. Your agent's core capabilities—analyzing link data, checking domain authority—are tied to your code, not a specific AI provider.

Fail Loudly, Not Silently with Pydantic AI

Imagine you're running a backlink audit with `list_links`. If the upstream API returns a malformed entry in the middle of a 10,000-link list, most agents would crash or, worse, silently ignore it. Pydantic AI stops everything and tells you exactly what went wrong. This focus on correctness is critical for automated SEO tasks. You know your agent's report is complete because if it wasn't, the program would have failed with a clear error message.

Setup guide

Set up Mozscape 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": {
        "mozscape-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Mozscape 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 Moz. 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 Mozscape 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 Mozscape MCP in Pydantic AI

Correctness. Pydantic AI validates every piece of data from the Mozscape API, so your agent will never operate on malformed or unexpected results from tools like `fetch_brand_authority`.

If the API adds a new, optional field, your code will continue to work. If it makes a breaking change, like renaming 'spam_score' to 'spamScore', your agent will raise a `ValidationError` on the next call, alerting you immediately to the issue.

Yes, it's the ideal use case. Your agent can use `fetch_link_status`, and Pydantic AI guarantees the response is a clean boolean. You'll never have to write defensive code to handle `None` or other unexpected return values.

It does. Because Pydantic AI is model-agnostic, you can connect this Mozscape server to an agent running on a local Ollama or Llamafile instance. The tool calls and data validation work exactly the same.

Your API key is managed by Vinkius and never exposed to the client. Each request for SEO metrics or link data runs in an ephemeral, single-use container that is destroyed after the API call completes, ensuring your query data is not persisted.

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