cloudflare-dns-mcp
MCP server for managing Cloudflare DNS subdomains, enabling an LLM to check availability, claim, release, and list subdomains under a root domain.
README
cloudflare-dns-mcp
An MCP server that lets an LLM check, claim, release, and list subdomains under a root domain, backed by the Cloudflare DNS API. Runs over stdio (local, default) or streamable HTTP (remote, behind a bearer token).
Tools
- check_subdomain_availability — check whether
<subdomain>.<root_domain>already has a DNS record. - request_domain — claim
<subdomain>.<root_domain>by creating an A record pointing at an IPv4 address. Fails if the subdomain is already taken. - release_subdomain — delete the DNS record for
<subdomain>.<root_domain>, freeing it up again. - list_subdomains — list every record under
<root_domain>currently registered.
Setup
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
Copy .env.example to .env and fill in your Cloudflare credentials:
cp .env.example .env
| Variable | Required | Description |
|---|---|---|
CLOUDFLARE_API_TOKEN_DNS |
yes | Cloudflare API token with Zone:DNS:Edit permission for the target zone. |
CLOUDFLARE_ZONE_ID |
yes | Zone ID of the domain in Cloudflare. |
CLOUDFLARE_ROOT_DOMAIN |
yes | Root domain that subdomains are created under, e.g. example.com. |
CLOUDFLARE_API_BASE_URL |
no | Overrides the Cloudflare API base URL. Defaults to https://api.cloudflare.com/client/v4. |
Running
By default the server runs over stdio, meant to be launched by an MCP client rather than run standalone:
python main.py
To run it as a standalone remote server over streamable HTTP instead, set MCP_TRANSPORT=http
plus a shared-secret MCP_HTTP_TOKEN (see .env.example):
MCP_TRANSPORT=http MCP_HTTP_HOST=0.0.0.0 MCP_HTTP_PORT=8000 MCP_HTTP_TOKEN=a-long-random-secret python main.py
MCP_HTTP_TOKEN is required in HTTP mode — the server refuses to start without it, since it
can create and delete DNS records and must not be exposed unauthenticated. Every request needs
Authorization: Bearer <token>; requests without it (or with the wrong token) get a 401. Put a
reverse proxy with TLS in front of it if it's reachable from the public internet.
Claude Code
claude mcp add cloudflare-dns /path/to/.venv/bin/python /path/to/main.py \
--env CLOUDFLARE_API_TOKEN_DNS=your-token \
--env CLOUDFLARE_ZONE_ID=your-zone-id \
--env CLOUDFLARE_ROOT_DOMAIN=example.com
Or add it by hand to .mcp.json (project scope) or ~/.claude.json (user scope):
{
"mcpServers": {
"cloudflare-dns": {
"command": "/path/to/.venv/bin/python",
"args": ["/path/to/main.py"],
"env": {
"CLOUDFLARE_API_TOKEN_DNS": "your-token",
"CLOUDFLARE_ZONE_ID": "your-zone-id",
"CLOUDFLARE_ROOT_DOMAIN": "example.com"
}
}
}
}
If the server is running remotely over HTTP instead:
claude mcp add --transport http cloudflare-dns https://your-host/mcp \
--header "Authorization: Bearer your-mcp-http-token"
or in .mcp.json:
{
"mcpServers": {
"cloudflare-dns": {
"type": "http",
"url": "https://your-host/mcp",
"headers": {
"Authorization": "Bearer your-mcp-http-token"
}
}
}
}
opencode
Add to opencode.json (project) or ~/.config/opencode/opencode.json (global):
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"cloudflare-dns": {
"type": "local",
"command": ["/path/to/.venv/bin/python", "/path/to/main.py"],
"enabled": true,
"environment": {
"CLOUDFLARE_API_TOKEN_DNS": "your-token",
"CLOUDFLARE_ZONE_ID": "your-zone-id",
"CLOUDFLARE_ROOT_DOMAIN": "example.com"
}
}
}
}
If the server is running remotely over HTTP instead, use type: "remote":
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"cloudflare-dns": {
"type": "remote",
"url": "https://your-host/mcp",
"enabled": true,
"headers": {
"Authorization": "Bearer your-mcp-http-token"
}
}
}
}
Other MCP clients
Generic stdio client config:
{
"mcpServers": {
"cloudflare-dns": {
"command": "/path/to/.venv/bin/python",
"args": ["/path/to/main.py"],
"env": {
"CLOUDFLARE_API_TOKEN_DNS": "...",
"CLOUDFLARE_ZONE_ID": "...",
"CLOUDFLARE_ROOT_DOMAIN": "example.com"
}
}
}
}
Generic streamable HTTP client config:
{
"mcpServers": {
"cloudflare-dns": {
"type": "http",
"url": "https://your-host/mcp",
"headers": {
"Authorization": "Bearer your-mcp-http-token"
}
}
}
}
Security
Never commit your .env file — it contains a Cloudflare API token that can edit DNS records
for your zone. .gitignore already excludes it; only .env.example (with placeholder values)
is tracked.
If you run the HTTP transport, MCP_HTTP_TOKEN is the only thing standing between the
internet and DNS write access to your zone — treat it like the Cloudflare token itself
(long/random, not committed, rotated if it ever leaks), and put it behind TLS.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.