How is this different from connecting Cloudflare API MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the Cloudflare API MCP API changes?

We track the Cloudflare API MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different Cloudflare API tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in Cloudflare API?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the Cloudflare API MCP server myself?

No. TrustGate connects to the Cloudflare API MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to Cloudflare API directly.

Connect Cloudflare API MCP to your AI agents, securely.

Q: Is Cloudflare API MCP secure?

The server itself exposes 4 tools, and some of them can write to your Cloudflare API account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches Cloudflare API.

One secured endpoint for every Cloudflare API call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try Cloudflare API MCP now

What your agents can ask once Cloudflare API MCP is connected.

“Which account am I authenticated as?”
“Find the endpoint for listing DNS records”
“Show the zones in this account”

“Search the Cloudflare docs for Zero Trust policies”
“List the R2 buckets through the API”
“Find the endpoints related to firewall rules”

Select the tools your AI agents can call

4 tools from the Cloudflare API MCP schema.

Showing 4 tools

searchreadWrite JavaScript to query spec.paths and find Cloudflare API endpoints.
executehigh riskWrite JavaScript to call cloudflare.request() with the discovered endpoints. The generated code runs in an isolated sandbox.
docsreadSearch Cloudflare developer documentation.
whoamireadReturn the Cloudflare user or account this connection is authenticated as.

What Cloudflare API MCP exposes

Cloudflare API MCP groups its 4 tools into 2 categories, each with a suggested starting policy.

Category	Covers	Access	Suggested policy
Code Mode	Endpoint discovery and execution against the full Cloudflare API through generated JavaScript	Read / Write	Approve execute; the generated code can reach any permitted endpoint
Account & Docs	Authenticated identity and developer documentation search	Read	Allow documentation searches