Runlayer named to Rising in Cyber 2026 List by Morgan Stanley →

Engineering

Runlayer Product Update: 1.25.0

Runlayer Product Update: 1.25.0

This update is about momentum: moving faster in the CLI, getting clearer visibility into what’s running, and debugging with less friction. Expect smoother workflows, better control, and fewer surprises as you build and ship.

Highlights

Catalog & Runlayer Deploy Updates

New connectors added: Braintrust, Gong, Snowflake (with full OAuth support!), Lever, Workday, Salesforce, Socket.dev, Scanner.dev, Amplitude, HuggingFace, BrowserUse, Heroku, CrowdStrike Falcon, and Microsoft Agent 365
Runlayer Deploy now lets you launch supported connectors straight from the Catalog - fewer steps and less copy/paste to get a server running.
Clearer deployment status makes it easier to tell when a deployment is finished vs when the server is actually ready after cold starts. Includes a new Trigger Deployment button for manual re-deployments.

MCP Watch: plug into your current MDM to uncover shadow MCP

Admins can now see where unmanaged ("shadow") MCP servers are being configured on devices—plus trends over time and where managed alternatives exist.
MCP Watch Re-analysis: Admins can now trigger re-analysis of discovered servers directly from the UI.
MDM-friendly deployment: a lightweight, self-contained script that keeps itself updates and runs on whatever schedule you define—completing in under 10 seconds.
Shadow MCP discovery is surfaced in Analytics, including discovery trends and "managed available" migration opportunities.
Shadow MCPs are categorized to help you prioritize: new/unknown servers vs "managed available" servers you can migrate to Runlayer-managed alternatives.
Click through to see affected users and drill down into audit logs for investigation.

Connector metrics: tool call health, usage, and performance

A new Metrics tab on connector details makes it easier to understand how a connector is behaving over time.
Track tool call success rate and failures, plus security violations.
See which tools are most used, slowest, or most failure-prone—and which clients are driving traffic.

Agents Accounts (Beta): programmatic access for your AI apps

Agents Accounts let you register AI applications as first-class clients in Runlayer, so they can authenticate programmatically and call MCP tools through the platform.

Microsoft Agent 365 Integration

Full OAuth broker support and catalog servers for Microsoft Agent 365, making it easy to connect your Microsoft-powered AI agents to Runlayer.

Skills: safer authentication and smoother setup

Skills now support OAuth authentication, expanding what can be connected safely and reducing setup friction in more environments.
OAuth-authenticated Skills enable more secure connections without relying on long-lived secrets.
Skills UX continued to improve, including better control over tooling behavior and setup flows.

For the complete list of changes, visit the Changelog.

Jan 23, 2026

•

Engineering

Read more

Runlayer and Anthropic MCP Tunnels: connecting Claude to systems behind your firewall

Runlayer and Anthropic MCP Tunnels: connecting Claude to systems behind your firewall

Runlayer and Anthropic collaborated on MCP Tunnels, which invert the connection direction so your network reaches out to Anthropic instead of exposing inbound ports, removing the security wall that blocks Claude from accessing internal systems like Jira, databases, and telemetry.

Don’t build your own MCP gateway

Don’t build your own MCP gateway

Senior engineers look at an MCP gateway and see a reverse proxy with auth and logs. That instinct is wrong. MCP attack vectors shift constantly, performance breaks at scale in specific ways, and threat detection requires MCP-specific signals that generic tools miss.

Fine-Grained Permissions and Identity Management for AI Agents

Fine-Grained Permissions and Identity Management for AI Agents

MCP adoption has exploded inside enterprises, with shadow servers and over-provisioned agents creating an attack surface most security teams haven't caught up to. Traditional IAM, OAuth, and RBAC weren't built for non-deterministic agents that delegate to other agents.

Runlayer named to Rising in Cyber 2026

Runlayer named to Rising in Cyber 2026

Runlayer was named to Notable Capital & Morgan Stanley's 2026 Rising in Cyber list, voted on by 150 sitting CISOs. Andy Berman on why the recognition matters, and what it signals about how AI-native companies are getting built.

Why production AI systems need MCP gateways

Why production AI systems need MCP gateways

An MCP gateway acts as the centralized proxy layer for agent-to-tool communications, handling tool discovery, authentication, input/output filtering, and observability across an organization's agentic systems.

The MCP STDIO RCE class, and why Runlayer doesn't run what the LLM asks it to

The MCP STDIO RCE class, and why Runlayer doesn't run what the LLM asks it to

OX Security found a design-level flaw in Anthropic's Model Context Protocol. MCP's STDIO transport turns a config file into a command executor. Here's how Runlayer's control plane breaks each of the four attack vectors.

Runlayer and AARM Partner to Secure Enterprise Agents

Runlayer and AARM Partner to Secure Enterprise Agents

Runlayer achieves AARM Extended Conformance (R1–R9), partnering with the Vanta-backed open specification to define how enterprises secure AI agents at runtime.

What Project Glasswing means for enterprise security

What Project Glasswing means for enterprise security

What Project Glasswing and Claude Mythos mean for enterprise security teams, and why your patch workflows, dependency management, and MCP governance need to evolve now.

The Danger of Fake MCP Servers

The Danger of Fake MCP Servers

Fake MCP servers pose a growing security risk, enabling data leaks, tool poisoning, and compromised AI behavior. Learn how these attacks work and how organizations can prevent them with proper controls and monitoring.

Runlayer + 1Password: Secure Credential Access for AI Agents

Runlayer + 1Password: Secure Credential Access for AI Agents

Runlayer and 1Password partner to bring secure, auditable credential access to autonomous AI agents. The integration lets enterprises inject secrets from 1Password vaults into agent sessions managed by Runlayer, replacing plaintext .env files with centralized governance, real-time retrieval, and full audit logging across human and non-human identities.

Honestly, MCP doesn’t “suck”

Honestly, MCP doesn’t “suck”

Garry Tan recently argued that MCP “sucks,” citing context-window bloat and weak authentication. This article breaks down why those criticisms miss the mark—and why MCP remains the better foundation for agents operating at enterprise scale.

FGA is not enough for your agent authorization

FGA is not enough for your agent authorization

PBAC beats FGA for agent authorization — context-aware, auditable, asymmetric access control without graph complexity.

Scale MCP with Dynamic Tool use

Scale MCP with Dynamic Tool use

Dynamic tool use cuts token waste from MCP by replacing bulk tool loading with lightweight search, saving cost without custom implementation.

OpenAI Agent Builder’s MCP Problem

OpenAI Agent Builder’s MCP Problem

OpenAI AgentKit/Agent Builder launched in Oct 2025 but, despite early hype, its limited integrations and weak security (e.g., unverified MCP servers, no namespace isolation, insufficient guardrails) create a large enterprise attack surface—prompting calls for controls like a trusted MCP catalog, tool gateway auditing, RBAC/least privilege, and stronger governance (e.g., via Runlayer).

Pwning OpenClaw in 50 Messages: Social Engineering Claude Opus Into Handing Over the Keys

Pwning OpenClaw in 50 Messages: Social Engineering Claude Opus Into Handing Over the Keys

A Claude Opus–powered OpenClaw agent with Slack and shell access was social-engineered in ~50 messages to rebind its UI, install ngrok, expose the dashboard publicly, reveal its gateway token, and approve the attacker’s device.

Unpacking the OWASP Top 10 for MCP

Unpacking the OWASP Top 10 for MCP

An overview of the OWASP MCP Top 10, highlighting the biggest security risks in MCP-enabled AI systems and the key safeguards teams can use to prevent them.

MCP Apps highlight the power of protocol governance

MCP Apps highlight the power of protocol governance

MCP Apps let tools render interactive UIs directly in chat via the same MCP protocol—not a new execution path. With Runlayer intercepting tool calls, resource fetches, and auth headers, existing MCP security controls apply from day one.

Announcing Box and Runlayer's partnership on Enterprise MCP

Announcing Box and Runlayer's partnership on Enterprise MCP

Connect AI agents to Box content with enterprise security. The official Box MCP server is live in the Runlayer marketplace, with identity enforcement, audit logging, and threat detection built in. Box customers can find Runlayer in the Box Integrations Center. Setup takes minutes.

Aidan Sochowski

MCP vs CLI Tools: Which is best for production applications?

MCP vs CLI Tools: Which is best for production applications?

CLI tools feel familiar to AI agents, but they break down in production due to brittle syntax, poor state management, and dangerous security assumptions. This post explains why CLI-based agent workflows fail and how a single-tool MCP using a known programming language offers a more reliable and secure alternative.

MCP Prompt Injection Attacks: How to Protect Your AI Agents

MCP Prompt Injection Attacks: How to Protect Your AI Agents

Two near-invisible prompt injection attacks showed how attackers can bypass default enterprise guardrails and trigger silent, ongoing data exfiltration by exploiting user and model trust. Runlayer blocks these attacks by treating every input as untrusted until it passes continuously updated security models trained on the latest real-world exploits.

Cursor Hooks + MCP Security: Official Runlayer Partnership Announcement

Cursor Hooks + MCP Security: Official Runlayer Partnership Announcement

Runlayer is an official Cursor Hooks launch partner. With Cursor Hooks, securely allow or deny MCP tool calls with Runlayer's enterprise MCP platform.

Marcin Jan Puhacz

The main takeaways from GitHub’s MCP Vulnerability

The main takeaways from GitHub’s MCP Vulnerability

GitHub’s MCP vulnerability revealed how AI agents can be weaponized through poisoned context in public repositories. This post analyzes the exploit, explains why permissions alone aren’t enough, and shares practical guardrails for preventing and mitigating agent-driven data exfiltration.

Runlayer Joins Anthropic, OpenAI, & Google as AAIF Founding Member

Runlayer Joins Anthropic, OpenAI, & Google as AAIF Founding Member

The Linux Foundation has launched the Agentic Artificial Intelligence Foundation (AAIF), with Runlayer joining sponsors Anthropic, OpenAI, Google, AWS, Microsoft. AAIF now oversees the Model Context Protocol (MCP), reinforcing MCP as a rising standard for AI agent integration. Runlayer supports AAIF’s open, secure, and scalable AI development mission.

Runlayer Raises $11M to Scale Enterprise MCP Infrastructure

Runlayer Raises $11M to Scale Enterprise MCP Infrastructure

MCP Security Risks: Your AI Agent is Probably Leaking Data Right Now

MCP Security Risks: Your AI Agent is Probably Leaking Data Right Now

MCP adoption is accelerating across major platforms, but security risks—like malicious servers, prompt injection, and tool-level exploits—are growing just as fast. This post breaks down real attack scenarios that show how easily data can leak when MCP implementations are trusted by default. It also outlines practical defenses for users and builders, plus why companies need audited MCP catalogs, gateway proxies, and sandboxing to stay secure at scale.

Why MCP builders are transitioning from DCR to OAuth CIMD

Why MCP builders are transitioning from DCR to OAuth CIMD

Over the last year, MCP has surged in adoption. To little surprise, this has introduced some scaling issues. One of these is client registration; previously, systems were rigged together by humans. Today, AI agents discover and interface with MCP servers freely, requiring a new paradigm for client communications.

What is Dynamic Client Registration?

What is Dynamic Client Registration?

Tired of manually registering every AI agent with every OAuth server? Dynamic Client Registration (DCR) lets your agents authenticate with MCP servers at runtime, no human clicks required. Learn how DCR works, when to use it over traditional OAuth, and why it's becoming essential for scalable agentic systems.