How is this different from connecting Cloudflare Observability 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 Observability MCP API changes?

We track the Cloudflare Observability 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 Observability 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 Observability?

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 Observability MCP server myself?

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

Connect Cloudflare Observability MCP to your AI agents, securely.

Q: Is Cloudflare Observability MCP secure?

The server itself exposes 8 tools, and some of them can write to your Cloudflare Observability 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 Observability.

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

Get started for free

Get a demo

Try Cloudflare Observability MCP now

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

Select the tools your AI agents can call

8 tools from the Cloudflare Observability MCP schema.

Showing 8 tools

query_worker_observabilityreadQuery the Workers Observability API to analyze logs and metrics from your Cloudflare Workers. Supports listing events, calculating metrics, and finding specific invocations.
observability_keysreadDiscovers available data fields in your Workers logs, including metadata fields, worker-specific fields, and custom logged fields.
observability_valuesreadFinds available values for specific fields in Workers logs to help build precise filters for analytics queries.
workers_listreadList all Workers in your Cloudflare account.
workers_get_workerreadGet the details of a Cloudflare Worker.
workers_get_worker_codereadGet the source code of a Cloudflare Worker.
search_cloudflare_documentationreadSearch the Cloudflare documentation.
migrate_pages_to_workers_guidereadRead the guide before migrating Pages projects to Workers.

What Cloudflare Observability MCP exposes

Cloudflare Observability MCP groups its 8 tools into 3 categories, each with a suggested starting policy.

All 8 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Observability	Log and metric queries, field key discovery and value exploration	Read	Limit access to intended accounts
Workers	Worker listing, details and source code	Read	Restrict access to source code
Account & Docs	Account listing, documentation search and migration guides	Read	Allow documentation searches

Connect Cloudflare Observability MCP to your AI agent

Four steps, under ten minutes.

01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
03
Connect Cloudflare Observability
Find Cloudflare Observability in the tool list and connect it.
04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.

Permissions down to the single tool

You do not allow Cloudflare Observability MCP or block it. You allow the exact tools each agent can call, one by one.

Cloudflare Observability MCP	8 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 8 tools

Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
Default denyA tool you have not enabled is never exposed to the agent.
Approval on writesTools that change or delete things can require a human to confirm.

Is Cloudflare Observability MCP secure?

One endpoint instead of raw credentials. Every call is checked against policy and logged.

AI agentsConnect through your MCP client configuration.	NeuralTrustApply controls based on your configuration.	Cloudflare Observability MCP8 documented tools.
Coding assistants	Connection & credentialsper user	Observability3 tools
Internal copilots	Tool access policiesdeny by default	Workers3 tools
Workflow automations	Request & response inspectioninline	Account & Docs2 tools
Compatible MCP clients	Activity monitoringalerts and logs