How to Use the Cloudflare Tunnel MCP in Pydantic AI

Q: How do I register the Cloudflare Tunnel MCP Server in my Pydantic AI project?

Install the slim package with pip install "pydantic-ai-slimmcp". Then, initialize MCPToolset with your Vinkius HTTP endpoint and pass it to the Agent constructor via the toolsets argument.

Q: Can Pydantic AI validate the structure of a Cloudflare Tunnel token?

Yes, when the agent calls gettunneltoken or getmanagementtoken, the returned tokens are validated against strict Pydantic schemas, ensuring your application only handles valid, well-formed credentials.

Q: How do I filter tunnels securely using this setup?

Use listtunnels to retrieve and filter your tunnels. The resulting list is parsed into typed models, allowing your agent to safely inspect tunnel metadata.

Run type-safe Cloudflare Tunnel management in Pydantic AI with strict schema validation on every network change.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cloudflare Tunnel MCP to Pydantic AI

Create your Vinkius account to connect Cloudflare Tunnel 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 Cloudflare Tunnel with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe tunnel provisioning in Pydantic AI

Network configuration cannot tolerate silent errors or half-baked parameters. This MCP Server integrates with Pydantic AI, forcing every response from tools like `create_tunnel` and `create_route` to validate against strict runtime schemas before your agent acts on them. If the Cloudflare API returns unexpected payload structures, Pydantic AI immediately halts execution with a validation error. This prevents your agent from attempting to use malformed tunnel tokens or invalid routes in your production code.

Rigorous configuration updates via Pydantic AI

Updating routing tables requires absolute precision. Your agent can pull the latest configuration with `get_configuration`, validate the schema, and safely push updates using `put_configuration` and `update_route`. Because every field is type-checked, the agent cannot hallucinate non-existent routing parameters. You can trust the agent to run `update_tunnel` without worrying about corrupting your Zero Trust network architecture.

Deterministic connection monitoring and teardown

Keep your network clean with predictable cleanup routines. Your agent can list all active connections using `list_connections` and parse the output into strongly-typed Pydantic models to verify network health. Once validation passes, the agent can clean up inactive links with `cleanup_connections` or completely tear down assets using `delete_tunnel` and `delete_route`. This ensures your network state matches your application's internal data models exactly.

Setup guide

Set up Cloudflare Tunnel 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": {
        "cloudflare-tunnel-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install the slim package with `pip install "pydantic-ai-slim[mcp]"`. Then, initialize `MCPToolset` with your Vinkius HTTP endpoint and pass it to the `Agent` constructor via the `toolsets` argument.

The framework will catch the error, and because the MCP Server outputs clean, structured data, your agent can inspect the failure using tools like `get_connector` to diagnose the issue without crashing silently.

Yes, when the agent calls `get_tunnel_token` or `get_management_token`, the returned tokens are validated against strict Pydantic schemas, ensuring your application only handles valid, well-formed credentials.

Use `list_tunnels` to retrieve and filter your tunnels. The resulting list is parsed into typed models, allowing your agent to safely inspect tunnel metadata.

Your Cloudflare Tunnel tokens, route definitions, and configuration files are processed inside Vinkius's secure, ephemeral V8 sandbox. Pydantic AI validates these data types in your local runtime, ensuring sensitive network credentials never touch third-party storage.

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