cloudflareAug 14, 2026

How Cloudflare detects MCP traffic and helps secure it (opens in new tab)

AI agents change the risk model for resource permissions because they make nondeterministic decisions and can repeat actions at machine speed. A mistaken judgment that a human might quickly catch can become thousands of harmful operations before anyone notices. Cloudflare’s new Cloudflare One capabilities aim to detect MCP traffic, identify its users and servers, and enforce approved routes through MCP Server Portals. ## Why AI Agents Require New Controls - Traditional permissions assumed users would apply judgment and act at a limited human pace. - AI agents can invoke tools repeatedly and indefinitely. - A single incorrect decision can rapidly propagate across databases, SaaS systems, or infrastructure. - MCP makes it easy to connect clients such as Claude Code, Codex, Cursor, OpenCode, and VS Code to approved or unapproved tools. - Direct MCP traffic can resemble ordinary HTTPS because MCP does not require a standard hostname or `/mcp` path. ## Anatomy of an MCP Tool Call An MCP request appears differently at three points: - **Client:** The agent decides to invoke a tool and supplies arguments. - **Network:** The request is transmitted as an HTTP transaction containing JSON-RPC. - **Server:** The server authenticates, validates, and dispatches the request to a tool handler. Useful protocol signals include: - Destination hostname and path - Authorization credentials - `MCP-Protocol-Version` - `Mcp-Method` - `Mcp-Name` - JSON-RPC request `id` - Tool arguments in `params` The tool name indicates the intended operation, while the arguments may contain sensitive data such as source code, customer information, search queries, or infrastructure-changing instructions. Responses can also contain sensitive results, making both request prevention and response inspection valuable. ## Controls Inside the MCP Client Client hooks can intervene after the model selects a tool but before the request is serialized. - Enforce server allowlists - Require confirmation for sensitive operations - Remove sensitive data from arguments - Support local `stdio` MCP servers that never generate network traffic The main limitation is operational: organizations must implement controls across every client employees use. Client telemetry also cannot provide a complete inventory unless the organization manages all relevant clients and devices. ## Controls at the Network Boundary A secure web gateway with TLS decryption can inspect remote MCP traffic independently of the client. - Associate requests with users and devices - Inspect destinations and MCP protocol headers - Detect direct connections outside approved MCP Portals - Block unauthorized traffic before it reaches the server - Use data loss prevention scanning to inspect JSON-RPC methods and arguments Network controls provide the broadest visibility into remote MCP usage, but they cannot see local `stdio` calls or traffic that bypasses managed network paths. ## Controls at the MCP Server The server has the deepest execution context because it knows the authenticated caller, parsed message, resolved tool, and validated arguments. Server-side middleware can: - Authorize users for specific tools - Apply rate limits - Inspect arguments - Log outcomes - Block requests before tool execution Cloudflare’s WriteGuard applies this approach to internal MCP servers by assigning tools risk tiers and enabled or disabled states. It can allow reads, attach attribution and audit events to approved writes, or block critical actions before their handlers run. Because enforcement occurs on the server, users cannot bypass it by changing clients or disabling local hooks. ## Layered MCP Security Each control point has a different strength: - **Client controls:** Earliest intervention and support for local MCP, but limited coverage. - **Network controls:** Broadest visibility into remote traffic and unmanaged MCP connections. - **Server controls:** Richest context and final prevention point before execution. A layered strategy can protect sensitive data before it leaves a device, identify shadow MCP usage, require trusted Portal-based access, and prevent unauthorized tools from executing.

data-loss-preventionai-agentmodel-context-protocolaccess-control+4

cloudflareAug 5, 2026

Cloudflare is the only vendor named a Visionary in 2026 SASE and SSE reports (opens in new tab)

Cloudflare argues that SASE and SSE are entering a major transition driven by AI agents, shadow applications, post-quantum threats, and increasingly distributed workforces. It presents Cloudflare One as a unified, programmable platform designed to address these pressures without the fragmented architectures, complex deployments, and hidden costs associated with legacy vendors. The company cites its recognition as a Visionary in both Gartner’s 2026 SASE and SSE Magic Quadrants as validation of this approach. ## The SASE Market’s Architectural Gap - Many SASE platforms are assembled through mergers and acquisitions, creating disconnected products and difficult deployments. - Cloudflare’s “connectivity cloud” uses one global network to connect and protect employees, AI agents, and infrastructure. - AI security has focused primarily on human interactions with generative AI, leaving autonomous agents and MCP server sprawl insufficiently governed. - Cloudflare claims its SASE platform provides shared visibility and policy controls for both humans and AI agents, including limits on AI inference costs. - Post-quantum protection is presented as an immediate requirement against “harvest-now, decrypt-later” attacks, rather than a future concept. - Cloudflare emphasizes predictable SASE bundles instead of charging separately for advanced capabilities or remote and office use cases. ## Technological Pressures Reshaping SASE - **AI-generated applications:** Employees can rapidly create internal “vibe-coded” tools without IT oversight. SASE platforms will need to automatically apply zero trust access, WAF, API protection, and DLP. - **Autonomous AI agents:** Future systems must issue narrowly scoped credentials for individual tasks, evaluate agent intent, and detect abnormal tool-call activity. - **Post-quantum agility:** Organizations need adaptable post-quantum encryption now, while standards continue to evolve. Cloudflare says it aims to deliver a fully quantum-secure SASE platform by 2028. - **Architectural consolidation:** Genuine platform consolidation requires shared code, control, data, and infrastructure planes—not merely multiple products marketed as a single platform. - These changes are described as current customer requirements rather than distant predictions. ## Cloudflare’s Unified Architecture - Cloudflare says it built its SASE platform from the ground up on a single global network rather than combining unrelated security products. - A composable architecture allows new security capabilities to be introduced without waiting for lengthy integration cycles. - Administrators can use familiar SASE policies to secure human AI prompts, AI-agent connections, and MCP servers. - New AI applications can inherit existing zero trust controls instead of requiring security to be retrofitted later. ## Easier SASE Deployment - Legacy platforms often route traffic through multiple inspection points, producing “tromboning,” capacity-planning challenges, and complicated operations. - Cloudflare claims every service runs across its network, eliminating specialized appliance silos and reducing deployment complexity. - Common tasks—such as extending zero trust to an application, adding DLP to Gateway traffic, or connecting an office—are intended to take days or weeks rather than months or years. - The platform is positioned as operating more like a modern SaaS service than a collection of separately managed security engines. ## Programmable SASE - Cloudflare distinguishes true programmability from basic GUI automation and APIs layered over inflexible products. - Its SASE platform runs alongside the company’s edge developer platform, allowing customers to integrate custom code directly into the security fabric. - This design is intended to let organizations enrich access decisions with real-time signals and adapt policies to their own requirements. Cloudflare’s recommendation is effectively to choose SASE platforms built on unified, composable infrastructure that can govern people, applications, and autonomous agents together. Organizations should prioritize integrated policy enforcement, native post-quantum readiness, predictable pricing, and genuine programmability over loosely bundled legacy products.

data-loss-preventionzero-trustai-securitysase+3

cloudflareMay 21, 2026

Announcing Claude Compliance API support with Cloudflare CASB (opens in new tab)

Cloudflare is adding Claude Compliance API support to CASB, giving security teams visibility into Claude usage without endpoint agents or inline traffic inspection. The integration scans Claude organizations, projects, conversations, files, and artifacts for sharing issues and sensitive data, then surfaces findings in the Cloudflare dashboard. It also connects those findings to Cloudflare Gateway policies so teams can move from detection to enforcement. ## The Security Challenge of Enterprise AI - AI adoption has outpaced governance, leaving organizations with limited visibility into sanctioned tools. - Traditional controls may block unauthorized applications but cannot inspect activity inside approved AI platforms. - AI-specific risks include: - Employees entering customer or confidential data into prompts - Developers exposing API keys - AI-generated content containing company secrets - Files and data being shared through persistent conversations and agent workflows - Effective protection must cover the full lifecycle of AI data, including API usage, content handling, and data stored within applications. ## Cloudflare’s Layered AI Security Model - **Cloudflare AI Gateway** monitors requests, token usage, and model performance while supporting rate limits, caching, and routing controls. - **Cloudflare Gateway and Data Loss Prevention** inspect AI traffic and can block prompts containing personally identifiable information or confidential material. - **Cloudflare Access with MCP server portals** protects connections between agents and corporate systems, with centralized access control and audit logging. - **Cloudflare CASB** scans data stored inside Claude for misconfigurations and sensitive content through API integrations. ## Claude Compliance API Findings Cloudflare CASB connects to Anthropic’s Compliance API and displays findings alongside those from applications such as Microsoft 365, Google Workspace, and Salesforce. - **Projects:** Detect projects shared with an organization or selected users and groups. - **Project attachments:** Identify files and documents violating DLP policies. - **Chat files:** Scan user-uploaded and provider-generated files. - **Chat messages:** Inspect prompts and provider responses for sensitive data. - **Artifacts:** Detect sensitive information in AI-generated documents and files. - Findings are categorized, prioritized by severity, and handled through existing triage, assignment, and remediation workflows. ## Coverage for Claude Enterprise and Platform - For **Claude Enterprise**, CASB retrieves information about organizations, projects, chats, roles, messages, and uploaded files using read-only endpoints. - For **Claude Platform**, it continues to monitor member and workspace changes, API key creation, and file creation or download events. - Support for the Claude Platform Activity Feed is planned for a future release. ## From Detection to Enforcement - A finding such as a sensitive file upload can be converted into a Cloudflare Gateway policy. - Administrators can: - Block uploads to Claude for specific users - Restrict access to Claude entirely - Limit application functionality until the issue is resolved - This combines CASB’s visibility into stored data with Cloudflare’s inline policy enforcement. ## Getting Started - Organizations need a Claude Enterprise account. - They must request Compliance API access from Anthropic. - Once access is granted, the integration can be connected through Cloudflare CASB. Cloudflare’s recommendation is to combine CASB monitoring with Gateway, DLP, AI Gateway, and Access controls to govern AI usage across both traffic and stored data.

data-loss-preventionmcpanthropiccloudflare-ai-gateway+4

cloudflareApr 14, 2026

Securing non-human identities: automated revocation, OAuth, and scoped permissions (opens in new tab)

Cloudflare argues that securing modern infrastructure requires managing non-human identities—agents, scripts, and third-party applications—as carefully as human users. The core model combines principals, credentials, and policies, with protections covering token leakage, OAuth access visibility, and narrowly scoped permissions. The post focuses especially on automated token detection and revocation, designed to limit damage when credentials are exposed. ## Identity as Three Connected Components - **Principal:** The identity acting on a system’s behalf, such as a developer, AI agent, background service, or OAuth application. - **Credential:** The proof of identity, typically an API token. Anyone who obtains it may impersonate the principal. - **Policy:** The permissions assigned to the identity, determining which resources and actions it can access. - Security failures occur when these elements are managed separately—for example, when a valid identity uses a stolen token or has unnecessarily broad permissions. ## Automated Detection and Revocation of Leaked Tokens - API tokens are commonly exposed by accidentally committing them to public repositories. - Cloudflare cites GitGuardian’s estimate that more than 28 million secrets were published to public GitHub repositories in the previous year, with AI-driven development increasing leak rates. - Cloudflare is partnering with credential-scanning providers to detect leaked tokens and revoke them before attackers can exploit them. - New Cloudflare token formats use a recognizable `cf` prefix and a checksum, allowing scanners to identify tokens confidently and verify whether they are authentic. - Existing tokens remain valid, but newly generated tokens use the scannable format. ## GitHub Secret Scanning Integration - GitHub scans public and private repositories for the new Cloudflare token formats on every commit. - For public repository leaks: - GitHub validates the token using its checksum. - GitHub sends Cloudflare a webhook. - Cloudflare automatically revokes the token. - The user receives an email prompting them to create a replacement. - For private repositories, GitHub notifies the customer so the leaked credential can be removed and replaced. ## Protection Through Cloudflare One Cloudflare One customers can use the Credentials and Secrets DLP profile to detect and block Cloudflare tokens across multiple data paths: - **Network traffic:** Cloudflare Gateway can block tokens in uploads, downloads, and outbound requests. - **Email:** Cloudflare Email Security and the DLP Assist add-in can scan Microsoft 365 messages before external delivery. - **Stored data:** Cloudflare CASB scans connected services such as Google Drive, OneDrive, and Dropbox. - **AI traffic:** Cloudflare AI Gateway can inspect prompts and model responses in real time, addressing credential exposure through AI systems. ## Broader Scanner Ecosystem - Cloudflare is working with open-source and commercial credential-scanning tools. - The goal is to protect customers regardless of which repository or secret-scanning products they use. - Automatic revocation is presented as a critical safeguard because credential exposure is treated as inevitable rather than exceptional. Organizations should use recognizable, verifiable tokens, enable repository and DLP scanning, and ensure leaked credentials are revoked automatically. These controls reduce the window in which an exposed token can be used and should be combined with narrowly scoped permissions for agents and applications.

data-loss-preventioncloudflareoauthapi-security+4

cloudflareApr 14, 2026

Scaling MCP adoption: Our reference architecture for simpler, safer and cheaper enterprise deployments of MCP (opens in new tab)

Cloudflare argues that enterprise MCP adoption requires centralized governance rather than individually managed, locally hosted servers. Its reference architecture combines remote MCP servers, Cloudflare Access, MCP server portals, and AI security controls to improve visibility, authentication, policy enforcement, and performance. The company also introduces Code Mode with MCP server portals to reduce the token and context-window costs of exposing large APIs. ## Centralized Remote MCP Servers - MCP separates the AI application from corporate credentials and APIs: - The MCP client connects to the LLM or agent. - The MCP server mediates access to internal resources. - Cloudflare moved away from locally hosted MCP servers because they: - May use unvetted software and versions. - Increase supply-chain and tool-injection risks. - Are difficult for IT and security teams to administer. - A centralized team manages MCP infrastructure through a shared monorepo platform. - Approved teams can create governed MCP servers from templates, inheriting: - Default-deny write controls. - Audit logging. - Automated CI/CD pipelines. - Secrets management. - Servers are deployed remotely on Cloudflare’s developer platform and custom domains, providing centralized usage visibility and global low-latency access. ## Authentication with Cloudflare Access - Public MCP servers, such as documentation and Radar services, can remain openly accessible. - MCP servers connected to private corporate resources require employee authentication. - Cloudflare Access acts as the OAuth provider and identity layer. - It verifies: - Single sign-on. - Multifactor authentication. - IP address, location, and device-certificate context. - Access issues tokens that authorize users to reach protected resources. ## MCP Server Portals for Discovery and Governance - As the number of MCP servers grew, employees needed a central way to discover authorized services. - Users connect their MCP client to a portal, which exposes the internal and third-party MCP servers they are permitted to use. - Portals provide: - Centralized logging. - Consistent policy enforcement. - Data loss prevention controls. - Access policies for users and tools. - Administrators can restrict both portal access and the specific tools exposed by each server. - Finance users might receive only read-only repository tools. - Engineering users on corporate devices might receive read/write capabilities. - Portals support MCP servers hosted on Cloudflare as well as third-party servers. - Cloudflare emphasizes that the relevant security and networking components can run on the same physical machine in its global network, reducing latency and avoiding unnecessary traffic transit. ## Code Mode Reduces MCP Token Costs - The standard MCP design exposes every API operation as a separate tool. - For large platforms with thousands of endpoints, this exhaustive tool list consumes an agent’s context window and increases token costs. - Cloudflare presents Code Mode with MCP server portals as a way to address this scaling problem. - The provided article excerpt ends while introducing Cloudflare’s earlier use of server-side Code Mode for exposing large numbers of API endpoints. Cloudflare’s approach recommends treating MCP as enterprise infrastructure: centrally deployed, authenticated, discoverable, policy-controlled, and monitored. Organizations adopting MCP at scale should avoid unmanaged local servers and provide reusable platforms that make secure deployment the default.

data-loss-preventioncloudflareci-cdmodel-context-protocol+4

cloudflareMar 4, 2026

Defeating the deepfake: stopping laptop farms and insider threats (opens in new tab)

Trust is becoming a critical security weakness as attackers use stolen identities, AI-generated deepfakes, and laptop farms to impersonate remote workers. Traditional zero trust controls verify devices and credentials but often fail to verify the actual person behind them. Cloudflare’s partnership with Nametag adds identity verification during onboarding and risk-based controls afterward, aiming to prevent fraudulent workers from accessing corporate systems. ## The Rise of Remote Worker Fraud - Organized groups, including North Korean operations, use “laptop farms” to infiltrate companies. - Devices are shipped to domestic addresses, physically connected to KVM switches, and remotely operated by fraudulent workers. - Attackers use stolen identities, generative AI for interviews, and deepfake tools to create convincing government IDs and selfies. - Valid credentials and corporate-issued devices can make these users appear legitimate to standard zero trust systems. ## Why Traditional Insider Threat Defenses Fall Short - DLP and UEBA tools typically detect suspicious behavior only after an attacker has gained access. - Conventional onboarding often trusts: - The identity provided by a new hire - The shipping address receiving the laptop - Credentials sent to a personal email address - Zero trust policies commonly verify device posture, location, and account permissions—but not whether the person is genuinely the employee. ## Identity-Verified Zero Trust - Cloudflare Access is adding Nametag’s workforce identity verification to its existing policy checks. - Nametag verifies that the person receiving, configuring, and using a device is: - A real person - The legitimate person named in the identity documents - The authorized employee - Verification occurs before access to email, code repositories, or other internal resources is granted. ## How the Nametag Integration Works - Nametag integrates with Cloudflare Access through OpenID Connect (OIDC). - It can operate as the primary identity provider or as an additional evaluation factor alongside Okta or Microsoft Entra ID. - A typical onboarding flow includes: - The user attempts to access an onboarding portal. - Cloudflare redirects them to Nametag. - The user provides a work email, takes a selfie, and scans a government-issued ID. - Nametag’s Deepfake Defense technology uses cryptography, biometrics, and AI to detect fake identities, injection attacks, and presentation attacks such as printed photos. - A successful verification returns an ID token to Cloudflare, which applies its Access policies. - The process reportedly takes less than 30 seconds, and biometrics are not retained afterward. ## Layered Insider Threat Protection - Identity verification complements Cloudflare’s existing controls: - API-driven DLP for detecting data exfiltration - Remote Browser Isolation for reducing browsing risks - Shadow IT reporting and CASB capabilities for identifying unmanaged services and misconfigurations - Together, these controls distinguish between knowing which account is connecting and knowing who is actually behind the keyboard. ## Continuous Verification - Initial identity checks are not sufficient because legitimate credentials can later be sold or compromised. - Cloudflare Access uses user risk scores to support context-aware policies. - A sudden increase in risk can trigger access revocation for one or multiple applications. Organizations facing remote hiring and insider-threat risks should supplement device and credential verification with strong identity assurance at onboarding, followed by continuous, risk-based monitoring.

data-loss-preventionaicloudflarezero-trust+4

cloudflareMar 4, 2026

Stop reacting to breaches and start preventing them with User Risk Scoring (opens in new tab)

Cloudflare is adding User Risk Scores to Cloudflare One so access decisions can reflect a user’s recent behavior, not just identity and device posture. The system continuously combines security signals, assigns a deterministic risk level, and applies adaptive access policies in real time. This is intended to replace slow, manual incident response with continuous, automated protection. ## Continuous User Risk Scoring - Risk scores identify behaviors associated with compromised accounts or insider threats, including: - Impossible travel - Failed login attempts - Malware detections - Risky browsing - Data loss prevention (DLP) violations - Outdated or insecure devices - Cloudflare Access and Gateway provide internal telemetry such as login activity, location, malware events, and sensitive-data triggers. - Integrations with CrowdStrike and SentinelOne add third-party device and security signals. - Administrators choose which behaviors to monitor and assign each a low, medium, or high risk level. - A user’s score is based on the highest-risk enabled behavior detected during the relevant period. - Investigators can manually reset a score after reviewing an incident while retaining its historical record. ## Adaptive Access Policies - User Risk Score is now available as a condition in Cloudflare Access policies. - Organizations can create global or application-specific controls, such as: - Blocking high-risk users from financial applications - Requiring medium-risk users to authenticate with a physical security key - Automated enforcement reduces the delay involved in revoking sessions or changing identity-provider groups manually. - Policies can limit damage while allowing lower-risk users to continue working. ## Dynamic Enforcement and Integrations - Access can be revoked during an active session when a user’s risk increases. - Access is automatically restored when the score falls after investigation and clearance. - Cloudflare plans to explore enforcing step-up MFA during active sessions when risk changes. - Through the Shared Signals Framework, Cloudflare can send risk information to Okta so users restricted on the network are also restricted at the SSO entry point. Cloudflare recommends using User Risk Scores to make zero trust access continuously adaptive rather than evaluating users only at login. Existing customers can configure the feature in the Cloudflare One dashboard, while larger organizations can integrate partner telemetry through a ZTNA pilot.

data-loss-preventionzero-trustsasecloudflare-one+4

datadogOct 15, 2025

Failure is inevitable: Learning from a large outage, and building for reliability in depth at Datadog (opens in new tab)

Datadog’s March 2023 outage exposed a fundamental weakness in its reliability strategy: although 40–50% of production Kubernetes nodes remained operational, customers experienced the platform as entirely unavailable. The incident showed that preventing every failure is impossible and that systems must instead continue delivering useful, accurate service when components fail. Datadog consequently began redesigning products around graceful degradation, prioritizing data preservation, fresh information, and partial results. ## Lessons from the March 2023 Incident - An unsupervised global update triggered a restart interaction that disconnected roughly 50–60% of production Kubernetes nodes. - The web interface recovered quickly, but logs, metrics, alerts, traces, and other core features became unavailable. - Pages loaded without displaying customer data, creating a nearly complete outage from the user’s perspective. ## Limits of Traditional Root-Cause Analysis - Datadog identified the legacy global security-update mechanism as the immediate trigger and disabled it. - Fixing that mechanism alone could not address the broader class of failures caused by certificates, configuration changes, overloads, date-handling bugs, or other unexpected events. - The company concluded that resilience requires reducing the impact of failures, not merely preventing one specific failure mode. ## Why Partial Infrastructure Became a Total User-Facing Failure - Datadog’s systems historically favored complete correctness over partial visibility. - For example, metric queries could wait until all relevant tags were processed to avoid showing misleading values or triggering false alerts. - During a large outage, this behavior created a “square-wave” failure: missing some data caused the system to show no data. - Ordered queues could stall fresh results behind stuck work, retries could overload already-strained services, and node-specific processing could make surviving capacity ineffective. - The underlying design assumption was that systems should either function fully or stop, rather than degrade while continuing to provide value. ## Prioritizing Graceful Degradation Datadog shifted from relying primarily on redundancy and “never-fail” architectures to explicitly designing for inevitable failures. - Customer data should never be lost, even if delivery is delayed. - Fresh, real-time data should take priority over stale backlog processing. - Systems should provide partial but accurate results whenever possible instead of returning nothing. ## Persistent Storage at the Start of Processing Pipelines - The outage caused a limited but non-zero amount of irreversible customer data loss. - Some pipelines acknowledged data before writing it to replicated storage, leaving unreplicated data only in memory or on a local disk. - When a node failed, that data disappeared and could not be recovered through agent retries. - After the node loss, surviving intake nodes also struggled to write to downstream replicated stores. - Their memory and local-disk buffers eventually filled, causing additional data loss as the outage continued. - Datadog therefore identified persistent intake storage as a key requirement for preserving data during large-scale failures. The broader recommendation is to design systems not only to prevent outages, but also to remain useful during them: preserve every accepted event, prioritize current information, and expose accurate partial results instead of failing completely.

data-loss-preventiondatabase-designk8sgraceful-degradation+4