AI Defense Stack

Agent & MCP security

Cloudflare MCP Server Portals: managed MCP portal in Cloudflare One

MCP Server Portals is a managed MCP portal in Cloudflare One from Cloudflare. It is a commercial product offered as: SaaS, API. Pricing model: not published.

  • Last reviewed
Visit MCP Server Portals (opens in a new tab) Documentation (opens in a new tab)
Commercial Layer 7: Agent and tool access

Best for

Organizations on Cloudflare One that want employees' AI clients to reach approved remote MCP servers through one URL, with per-server access policies and tool allowlists

Consider instead if

  • You want to scan MCP servers for poisoned tools before approving them. See Cisco MCP Scanner.
  • You want a self-hosted open-source gateway rather than a Cloudflare-hosted portal. See agentgateway.

What MCP Server Portals does

Cloudflare MCP server portals is a feature of Cloudflare One, listed in the docs under Access controls and AI controls. A portal centralizes several remote MCP servers onto one HTTP endpoint, so users connect an MCP client to a single URL. Cloudflare Access policies decide which servers appear and who can connect. Admins can switch individual tools and prompts off, or hide everything by default and allow named items, and can rename tools without changing the upstream server. Optional routing through Cloudflare Gateway adds HTTP logging and DLP scanning, and each portal has request logs. The docs say it was previously called Agents Gateway, state no price and support remote HTTP servers only.

This summary is our own wording of the sourced facts on this page.

Key facts

Each value links to the page that states it, with the date we checked it.

Vendor
Cloudflare Source, checked October 21, 2026: developers.cloudflare.com (opens in a new tab)
Status
Active Source, checked October 21, 2026: developers.cloudflare.com (opens in a new tab)
Open source
No: closed source (proprietary) Source, checked October 21, 2026: developers.cloudflare.com (opens in a new tab)
Latest release
Not documented in the sources we checked
Deployment
SaaS, API Source, checked October 21, 2026: developers.cloudflare.com (opens in a new tab)
Pricing model
Not published in the sources we checked Source, checked October 21, 2026: developers.cloudflare.com (opens in a new tab)
Website
developers.cloudflare.com Source, checked October 21, 2026: developers.cloudflare.com (opens in a new tab)
Documentation
developers.cloudflare.com Source, checked October 21, 2026: developers.cloudflare.com (opens in a new tab)
API reference
Not documented in the sources we checked
Quickstart
developers.cloudflare.com Source, checked October 21, 2026: developers.cloudflare.com (opens in a new tab)
Security page
Not documented in the sources we checked
Attestations or disclosure
Not documented in the sources we checked

Capabilities

As documented by the vendor or project. The tag is our label from a controlled vocabulary.

Integrations

Where MCP Server Portals fits in our AI security layers

Our analysis

Our editorial model, not a standard. The primary layer follows the category, except for tools whose main documented job is detection and response; other layers rest on a capability the sources document. How the model works.

AI security layers that MCP Server Portals covers, with the role, how each applies and what it rests on
LayerRoleHow it appliesBased on
L7 Agent access Agent and tool access Primary Limit which tools, MCP servers, data and credentials an agent can use, and require approval for risky actions. Follows its category, Agent & MCP security
L8 Monitoring Monitoring and response Also covers Records each MCP request to a portal server, with Logpush export on Enterprise plans. Portal logs per portal or per server record time, status, server, capability and duration; Logpush export is Enterprise only

OWASP LLM Top 10 mapping

Our analysis

The risk list is OWASP's (Top 10 for LLM Applications, 2025). The mapping is our analysis, and each row rests on a capability the sources document.

OWASP LLM risks mapped to MCP Server Portals, with the capabilities each mapping rests on
RiskHow it appliesBased on
LLM02 Sensitive Information Disclosure Optional Gateway routing applies DLP scanning to portal traffic; blocked requests and responses return as errors. Cloudflare Access policies on each server control whether it appears in a portal, and policies on the portal control who can connect; Optional routing through Cloudflare Gateway adds HTTP logging, DLP scanning and egress policies to portal traffic; AI prompt profiles do not apply
LLM06 Excessive Agency Tool and prompt allowlists and Access policies limit which MCP servers and tools users and agents can reach. Admins can turn individual tools and prompts off, or hide all by default and allow named ones, and rename tools without changing the upstream server; Cloudflare Access policies on each server control whether it appears in a portal, and policies on the portal control who can connect; Optional routing through Cloudflare Gateway adds HTTP logging, DLP scanning and egress policies to portal traffic; AI prompt profiles do not apply

Not mapped in our analysis: LLM01, LLM05, LLM07. These are risks we expect tools in this category to cover; the sources we checked do not document a matching capability.

Alternatives and related tools

More in Agent & MCP security, ranked within the category by Coverage Score.

Cisco DefenseClaw

Cisco

Open sourceApache-2.0
  • CLI
  • Self-hosted

Scans skills and MCP servers, inspects agent tool calls and keeps an audit trail around AI coding agents.

Best for: Security teams that want scanning, guardrails and an audit trail around the coding agents developers already run, starting in observe mode before anything is blocked

Coverage Score 76 out of 100
  • LLM01 Prompt Injection
  • LLM02 Sensitive Information Disclosure
  • LLM06 Excessive Agency

Reviewed

Docker MCP Gateway

Docker

Open sourceMIT
  • CLI
  • Self-hosted

Proxies AI clients to MCP servers it runs as isolated Docker containers, with tool filters and call logs.

Best for: Developers and platform teams that already use Docker and want MCP servers to run in containers behind one gateway with per-server tool selection

Coverage Score 72 out of 100
  • LLM02 Sensitive Information Disclosure
  • LLM06 Excessive Agency

Reviewed

agentgateway

agentgateway (a Series of LF Projects, LLC)

Open sourceApache-2.0
  • CLI
  • Self-hosted
  • Cloud-native

Open-source proxy that applies auth, CEL policy and guardrails to LLM, MCP and agent-to-agent traffic.

Best for: Platform teams that want one open-source gateway in front of MCP servers and LLM providers, with token validation, CEL rules per MCP method and pluggable guardrails

Coverage Score 69 out of 100
  • LLM02 Sensitive Information Disclosure
  • LLM06 Excessive Agency

Reviewed

MCP Server Portals FAQ

Is this the same as Cloudflare AI Gateway?

The docs place MCP server portals under Cloudflare One, Access controls and AI controls, and the AI controls page does not mention AI Gateway. Cloudflare AI Gateway has its own entry in this directory.

Does it scan MCP servers or tool descriptions for attacks?

The docs page describes access policies, tool and prompt allowlists, logging and optional DLP scanning through Gateway. It does not describe scanning tool descriptions for poisoning.

What are the main limits?

Each portal supports up to 80 MCP servers and only remote HTTP servers. Device authentication is not supported, and AI prompt profiles do not apply to portal traffic.

Key facts you can cite

We have no commercial relationship with Cloudflare.

Sources & last reviewed

Last reviewed . We compile from the vendors' own public pages and repositories and we do not run the products. Source links open in a new tab. Found a mistake? Report a correction.