Bring Cloudflare Tunnel
to Pydantic AI
Learn how to connect Cloudflare Tunnel to Pydantic AI and start using 17 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the Cloudflare Tunnel MCP Server?
Connect your Cloudflare account to any AI agent to take full control of your Zero Trust connectivity and private network routing through natural conversation.
What you can do
- Tunnel Management — List all tunnels in your account, filter by status (healthy, degraded, down), and fetch detailed metadata for specific tunnels.
- Remote Configuration — Retrieve and update ingress rules and origin settings for remotely-managed tunnels without touching the CLI.
- Network Routing — Manage private network routes (CIDR) and IP-based routing to connect your internal resources securely.
- Connection Monitoring — Inspect active connectors, list tunnel connections, and clean up stale sessions to ensure high availability.
- Lifecycle Actions — Create new tunnels, update secrets, or delete decommissioned tunnels directly from your workspace.
How it works
- Subscribe to this server
- Enter your Cloudflare API Token (with Cloudflare Tunnel permissions)
- Start managing your secure tunnels from Claude, Cursor, or any MCP-compatible client
Who is this for?
- DevOps Engineers — quickly check tunnel health and update ingress rules during deployments without leaving the terminal or IDE.
- Security Teams — audit active tunnels and network routes to ensure compliance with Zero Trust policies.
- System Administrators — automate the cleanup of stale connections and monitor the status of remote connectors across multiple accounts.
Built-in capabilities (17)
If no client_id is provided, all connectors are removed. Clean up Cloudflare Tunnel connections
Create a tunnel route
Create a new Cloudflare Tunnel
Delete a tunnel route
Delete a Cloudflare Tunnel
Get configuration for a remotely-managed tunnel
Get Cloudflare Tunnel connector details
Get a Cloudflare Tunnel management token
Get tunnel route by IP
Get details for a single Cloudflare Tunnel
Get a Cloudflare Tunnel token
List Cloudflare Tunnel connections
List tunnel routes
List and filter Cloudflare Tunnels in an account
Add or update configuration for a remotely-managed tunnel
Update a tunnel route
Update an existing Cloudflare Tunnel
Why Pydantic AI?
Pydantic AI validates every Cloudflare Tunnel tool response against typed schemas, catching data inconsistencies at build time. Connect 17 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Cloudflare Tunnel integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Cloudflare Tunnel connection logic from agent behavior for testable, maintainable code
Cloudflare Tunnel in Pydantic AI
Cloudflare Tunnel and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Cloudflare Tunnel to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Cloudflare Tunnel in Pydantic AI
The Cloudflare Tunnel MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 17 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Cloudflare Tunnel for Pydantic AI
Every tool call from Pydantic AI to the Cloudflare Tunnel MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I update the ingress rules for a remotely managed tunnel?
Yes. Use the put_configuration tool to update the ingress rules and origin request settings for any tunnel that is configured for remote management.
How do I check if my tunnels are currently online?
You can use list_tunnels with the status parameter set to 'healthy' to see active tunnels, or use get_tunnel with a specific ID to see its current operational state.
Can I manage private network routes through this integration?
Yes. The server includes tools like list_routes, create_route, and delete_route to manage your Cloudflare Tunnel network routing (WARP-to-Tunnel).
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your Cloudflare Tunnel MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai
Explore More MCP Servers
View all →
GetFeedback
12 toolsManage online surveys, track real-time responses, and oversee feedback data via AI agents with GetFeedback.
Universal Unit Converter
4 toolsA zero-latency deterministic engine for exact physical conversions. Instantly convert weights, lengths, temperatures, and digital storage local.
Readwise
16 toolsConnect your AI agents to Readwise to manage books, highlights, tags, and spaced repetition reviews directly through natural language.
MapQuest
5 toolsMapping and location services via MapQuest — geocoding, directions, and POI search.