About Cloudflare Radar
Cloudflare Radar is an MCP server for AI agents and analysts querying internet traffic, attacks, routing, quality, domain rankings, and AI crawler activity. It offers both a standalone local server and a Pipeworx gateway endpoint.
Key features
- 01Internet quality summaries
- 02L7 DDoS attack breakdowns
- 03Top locations by traffic metrics
- 04Recent BGP route leaks
- 05Domain rankings and popular domains
- 06AI crawler traffic analysis
Use cases
- 01Review internet quality for a location and date range
- 02Inspect attack distribution across locations
- 03Check recent BGP route-leak events
- 04Assess domain popularity and AI crawler share
MCP support
Exposes Cloudflare Radar tools to MCP clients through a Pipeworx endpoint or a local stdio server. The gateway endpoint also includes shared Pipeworx meta-tools.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://gateway.pipeworx.io/cloudflare-radar/mcpclaude mcp add --transport http pipeworx-io-cloudflare-radar https://gateway.pipeworx.io/cloudflare-radar/mcp{"mcpServers":{"pipeworx-io-cloudflare-radar":{"type":"http","url":"https://gateway.pipeworx.io/cloudflare-radar/mcp"}}}Open in Cursor{"servers":{"pipeworx-io-cloudflare-radar":{"type":"http","url":"https://gateway.pipeworx.io/cloudflare-radar/mcp"}}}Open in VS Code{"mcpServers":{"pipeworx-io-cloudflare-radar":{"type":"http","url":"https://gateway.pipeworx.io/cloudflare-radar/mcp"}}}{"mcpServers":{"pipeworx-io-cloudflare-radar":{"serverUrl":"https://gateway.pipeworx.io/cloudflare-radar/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project README@pipeworx/cloudflare-radar
Cloudflare Radar MCP — internet observatory (traffic, attacks, BGP, quality).
Part of Pipeworx — an MCP gateway connecting AI agents to 1878+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
Tools
internet_quality(location?, date_range?)— IQI summary.attack_summary(dimension?, location?, date_range?)— L7 DDoS attack mix.top_locations(metric?, date_range?, limit?)— top countries by HTTP / DNS / attack share.bgp_leaks(date_range?, limit?)— recent BGP route-leak events.radar_domain_rank(domain, date?)— a single domain's popularity rank/bucket, category, and top locations. Answers "is this domain widely visited, or nowhere".radar_top_domains(limit?, location?, date?)— the most-visited domains globally or by country.radar_ai_bots(dimension?, date_range?, location?, user_agent?, limit?)— Cloudflare Radar AI bots: share of AI-crawler traffic (GPTBot, ClaudeBot, PerplexityBot, Bytespider, ...) by user agent, crawl purpose or industry. Unknownuser_agentreturnsfound:false.
Auth
- Platform key: gateway env
PLATFORM_CLOUDFLARE_RADAR_KEY(or reuseCLOUDFLARE_API_TOKEN). - BYO:
?_apiKey=<token>after creating one at https://dash.cloudflare.com/profile/api-tokens (no special scope required for Radar).
Data source
https://api.cloudflare.com/client/v4/radar/ — Bearer token.
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"cloudflare-radar": {
"url": "https://gateway.pipeworx.io/cloudflare-radar/mcp"
}
}
}
What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/cloudflare-radar/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1878+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
No MCP client? Call it over HTTP
curl -X POST https://gateway.pipeworx.io/v1/tools/internet_quality \
-H 'Content-Type: application/json' \
-d '{"location":"US","date_range":"7d"}'
No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/internet_quality. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
Standalone (no gateway account)
This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:
{
"mcpServers": {
"cloudflare-radar": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-cloudflare-radar"]
}
}
}
Or run it directly to confirm it starts:
npx -y @pipeworx/mcp-cloudflare-radar
It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call
for only this pack's tools — none of the shared meta-tools the gateway
connection above adds. Same source, same tools, no ask_pipeworx routing.
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Cloudflare Radar data" })
The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.