How to Use the Hexometer MCP in Pydantic AI

Q: How do I connect Hexometer tools to my Pydantic AI agent?

It's a one-liner. Install pydantic-ai-slimmcp, then create an MCPToolset with your Vinkius URL for this MCP server. Pass that toolset to your agent, and all 11 Hexometer tools are ready and type-checked.

Q: What happens if the Hexometer API changes?

Your Pydantic AI agent will raise a ValidationError the next time it calls a tool with a changed response. This is a feature, not a bug. It prevents your agent from working with bad data.

Q: Can I get a simple uptime status with Hexometer and Pydantic AI?

Yes, and you'll get a validated one. Calling getuptimestats will return a Pydantic model with fields for uptime percentage and response times. You can trust the data types are correct every time.

Q: Is it possible to list all my monitored sites with Hexometer and Pydantic AI?

Of course. The listmonitoredsites tool returns a validated list of your properties. Your agent can then iterate over this list with confidence, knowing each item conforms to your Pydantic model.

Get type-safe website monitoring. Connect to Hexometer with Pydantic AI and stop guessing API responses.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hexometer MCP to Pydantic AI

Create your Vinkius account to connect Hexometer 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 Hexometer with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Catch Errors with Confidence

Stop writing defensive code for messy API outputs. When your agent calls `check_page_errors` or `check_broken_links`, Pydantic AI guarantees the response is a clean, validated list of objects. You know exactly what fields to expect. If Hexometer's API ever returns something unexpected, your code doesn't fail silently. You get an immediate `ValidationError` that tells you exactly what went wrong. This is critical for building reliable agents that don't corrupt data.

Model-Agnostic Site Audits

Use whatever LLM works best for you. Pydantic AI isn't tied to one provider. You can use GPT-4, Claude 3, or a local model to drive your agent. The Hexometer tools will work the same way everywhere. This lets you build robust workflows. Have your agent run a `run_seo_audit`, and the structured Pydantic model it receives can be passed to any system. You're not locked into a proprietary data format. This MCP server just provides the validated data.

Build Correct-by-Construction Monitoring Agents

Define your agent's world with Pydantic models. When it calls `get_site_health`, the response—containing scores and status—is parsed into a model you've defined. There's no ambiguity. This approach is perfect for critical checks. You can trust the data coming from `get_security_status` or `get_uptime_stats` because it has passed runtime validation. It's the right way to build agents when correctness is more important than anything else.

Setup guide

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

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

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

It's a one-liner. Install `pydantic-ai-slim[mcp]`, then create an `MCPToolset` with your Vinkius URL for this MCP server. Pass that toolset to your agent, and all 11 Hexometer tools are ready and type-checked.

Your Pydantic AI agent will raise a `ValidationError` the next time it calls a tool with a changed response. This is a feature, not a bug. It prevents your agent from working with bad data.

Yes, and you'll get a validated one. Calling `get_uptime_stats` will return a Pydantic model with fields for uptime percentage and response times. You can trust the data types are correct every time.

Of course. The `list_monitored_sites` tool returns a validated list of your properties. Your agent can then iterate over this list with confidence, knowing each item conforms to your Pydantic model.

It is. The server is stateless and doesn't log your inputs or Hexometer's outputs. It just forwards your request for things like SEO audits or uptime stats, secured by your unique Vinkius auth token.

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