How to Use the Cloudflare Tunnel MCP in LlamaIndex

Q: How does LlamaIndex index Cloudflare Tunnel metadata without leaking secrets?

LlamaIndex only indexes structural metadata returned by listtunnels and listroutes. Sensitive credentials retrieved via gettunneltoken are automatically filtered out and never written to your vector database.

Q: How do I restrict the agent from deleting tunnels?

You can use the allowedtools filter when initializing the client in LlamaIndex. Simply exclude deletetunnel from the MCP tool list to ensure the agent only has read-only or configuration-only permissions.

Index your secure Cloudflare Tunnel configurations directly into LlamaIndex vector stores for semantic network querying.

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 LlamaIndex

Create your Vinkius account to connect Cloudflare Tunnel to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Cloudflare Tunnel Configurations in LlamaIndex

By calling `list_tunnels`, LlamaIndex ingests your entire network topology into a searchable vector index. Instead of guessing how your private network is set up, this MCP Server lets you index your entire network topology. When you ask your agent which services are exposed, it searches the indexed configuration data. It doesn't need to make live API calls every time because the historical configurations are stored locally for fast semantic retrieval.

Context-Aware Route Auditing

The `list_routes` tool lets LlamaIndex pull active paths and match them against your security documentation. Auditing routes requires comparing live state with your documented network policies. If the agent detects an undocumented route via `get_route_by_ip`, it flags the anomaly. The agent can then call `delete_route` to close the security gap based on its RAG analysis.

Smart Connector Troubleshooting

Your agent uses `get_connector` to pull diagnostic details when a tunnel goes down. The MCP Server pulls connector logs and details to build a diagnostic context for the LLM. The agent compares these live connector details with past successful configurations in your vector store. If a mismatch is found, it updates the configuration using `put_configuration` to restore the connection.

Setup guide

Set up Cloudflare Tunnel MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Cloudflare Tunnel MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Cloudflare Tunnel tools.",
)
response = await agent.run("List recent Cloudflare Tunnel data")

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 LlamaIndex

LlamaIndex only indexes structural metadata returned by `list_tunnels` and `list_routes`. Sensitive credentials retrieved via `get_tunnel_token` are automatically filtered out and never written to your vector database.

Yes, you can load your routing tables into a vector store using `list_routes`. This allows your agent to answer complex natural language questions about which private IPs are mapped to specific tunnels.

Yes, the agent can query past network incidents and compare them with live data from `get_connector`. This gives LlamaIndex the context it needs to recommend the exact `update_tunnel` parameters to fix a broken link.

You can use the allowed_tools filter when initializing the client in LlamaIndex. Simply exclude `delete_tunnel` from the MCP tool list to ensure the agent only has read-only or configuration-only permissions.

All routing tables and connector details fetched by the MCP Server are processed inside an isolated V8 sandbox. This ephemeral execution environment ensures that your private network architecture is never cached or stored on Vinkius servers after the tool execution finishes.

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