Runlayer named to Rising in Cyber 2026 List by Morgan Stanley →
Back to blog
Aidan Sochowski
Announcing Box and Runlayer's partnership on Enterprise MCP

Announcing Box and Runlayer's partnership on Enterprise MCP

Box and Runlayer are partnering to bring secure AI agent access to enterprise content. Starting today, the official Box MCP server is available in the Runlayer marketplace, and Runlayer is available in the Box integrations Center.

For organizations managing content in Box and adopting AI across their teams, this integration provides a governed path to connect the two.

The Integration

This is a two-way partnership:

In the Runlayer Marketplace: The official Box MCP server is now available for Runlayer customers. Enable it with one click and connect any MCP-compatible AI client to your Box content. Identity enforcement, audit logging, and security scanning are handled automatically.

In the Box Integrations Center: Runlayer is now listed as an official Box integration. Box administrators looking for an enterprise MCP platform can seamlessly enable access to Runlayer, with a streamlined setup path.

Why It Matters

AI agents are only as useful as the data they can access. For most enterprises, that means their contracts, reports, research, and documentation. The challenge is connecting AI to this content without creating security gaps or compliance risk.

Box has built the Intelligent Content Management platform that regulated industries trust. Runlayer has built the enterprise MCP platform that makes AI agent adoption enterprise-ready. Together, we are giving organizations a way to use AI with their most sensitive content, without compromise.

What This Enables

Teams using Box and Runlayer together can:

  • Query documents through AI. Ask questions across your Box content from Claude, ChatGPT, Cursor, or any MCP client, secured by Runlayer.
  • Build agentic workflows. Let AI agents leverage Box tools to ask questions, extract metadata, create folders and Hubs, and interact with Box content to complete complex tasks using skills in Runlayer.
  • Preserve existing access controls. Runlayer enforces Box permissions, so agents can only interact with content that users are authorized to access.
  • Maintain audit trails. Every agent interaction across clients with Box content is logged by Runlayer for compliance and security review.

For Regulated Industries

Both Box and Runlayer serve enterprises where security is not optional: financial services, healthcare, life sciences, legal. This integration preserves enterprise-grade security in Box while adding the MCP-specific protections that AI adoption requires, including threat detection for tool poisoning, prompt injection, and unauthorized data access.

Get Started

Box customers: Find Runlayer in the Box Integrations Center to connect your content to AI agents securely.

Runlayer customers: Enable the Box MCP server from your Runlayer connector catalog. Setup takes minutes.

The integration is live now.

Jan 27, 2026
 • 
Aidan Sochowski
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.
May 20, 2026
 • 
Andy Berman
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.
May 18, 2026
 • 
Alex Frazer
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.
May 18, 2026
 • 
Tal Peretz
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.
May 12, 2026
 • 
Andy Berman
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.
May 11, 2026
 • 
Tal Peretz
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.
Apr 22, 2026
 • 
Alex Frazer
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.
Apr 15, 2026
 • 
Tal Peretz
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.
Apr 11, 2026
 • 
Tal Peretz
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.
Apr 7, 2026
 • 
Tal Peretz
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.
Mar 17, 2026
 • 
Tal Peretz
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.
Mar 12, 2026
 • 
Vitor Balocco
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.
Mar 9, 2026
 • 
Alvaro Inckot
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.
Feb 20, 2026
 • 
Vitor Balocco
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).
Feb 19, 2026
 • 
Tal Peretz
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.
Feb 16, 2026
 • 
Alex Frazer
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.
Feb 10, 2026
 • 
Alex Frazer
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.
Jan 30, 2026
 • 
Tal Peretz
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.
Jan 25, 2026
 • 
Vitor Balocco
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.
Jan 23, 2026
 • 
Engineering
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.
Jan 19, 2026
 • 
Jake Moghtader
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.
Dec 18, 2025
 • 
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.
Dec 16, 2025
 • 
Vitor Balocco
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.
Dec 9, 2025
 • 
Andy Berman
Runlayer Raises $11M to Scale Enterprise MCP Infrastructure

Runlayer Raises $11M to Scale Enterprise MCP Infrastructure

Nov 17, 2025
 • 
Andy Berman
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.
Nov 12, 2025
 • 
Vitor Balocco
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.
Nov 7, 2025
 • 
Vitor Balocco
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.
Nov 6, 2025
 • 
Vitor Balocco
The fastest path to AI Transformation

Runlayer makes it easy to scale MCP, skills, and agents across your organization. Local or remote, every AI tool is secure, discoverable, and simple to manage.

Get an AI summary of this page
OpenAI logo featuring an abstract geometric knot design.Abstract symmetrical starburst shape with multiple elongated rounded spikes radiating from the center in dark gray.Abstract geometric logo consisting of symmetrical angular lines forming a star-like shape.
Solutions
Company
Resources
Connect
© Copyright 2026 Anysource Inc.
SOC 2 Certified
HIPAA Certified
GDPR Certified
Terms of Service
Privacy Policy