Lasso Releases First Open Source Security Gateway for MCP

Lasso, a leader in building Generative AI security solutions, announced today the launch of their open source MCP Gateway, the first security-centric solution for Model Context Protocol (MCP) specifically designed with agentic workflows development in mind. MCP Gateway accelerates secure, enterprise-grade adoption of MCP across the growing GenAI ecosystem, and is available as part of Lasso’s GenAI security platform, on GitHub and on other major open source platforms.

Since launched by Anthropic in November 2024, MCP has rapidly emerged as the de facto standard for connecting GenAI models with external tools and data sources. With thousands of developers contributing to the MCP ecosystem and a growing community on GitHub (e.g. Awesome MCP Servers with over 37K stars), Lasso offers foundational security tooling at this pivotal moment.

MCP simplifies AI-to-tool integrations across agentic workflows, enabling developers to build powerful LLM agents faster than ever. While this momentum continues to build, security and visibility have remained a major blind spot. Lasso MCP Gateway acts as a proxy and orchestrator for all MCP interactions, embedding critical security, governance, and monitoring capabilities while maintaining full compatibility with existing agent implementations.

“When MCP emerged, we immediately saw its revolutionary potential, but also recognized its security blind spots,” said Lior Ziv, CTO and Co-founder, Lasso. “That is why we built the world’s first MCP Gateway with security built-in to enable the continued innovation of agentic workflows. Lasso MCP Gateway makes it possible to scale GenAI agent development without compromising on safety, confidentiality, and transparency.”

Key Capabilities

Agnostic Guardrails

• Applies configurable security filters to both requests and responses

• Prevents sensitive data exposure before information reaches agents

• Works consistently across all connected MCPs regardless of their native capabilities

Advanced Tracking

• Provides usage analytics and pattern identification for optimization

Unified Visibility

• Provides a comprehensive dashboard for all MCPs in a single interface

Enterprise Readiness

• Empowers the community to add key enterprise features to the MCP Gateway

Watch the MCP Gateway demo video: https://www.youtube.com/watch?v=G8qNEOXqfX0

With the rapid rise of agentic workflows, organizations face wide range of risks including:

• Sensitive Data Exposure
  If outputs are not properly sanitized, tools can unintentionally leak secrets, credentials, or internal model states.

• Prompt Injection
  Hidden instructions that are embedded in tool descriptions or parameter hints, which the model unknowingly executes during runtime.

• Command Injection / Remote Code Execution
  Unvalidated inputs passed to shell commands or system calls can result in immediate remote code execution (RCE).

• Lack of Logging and Monitoring
  Without visibility into tool usage or model-tool interactions, detection and investigation of misuse becomes nearly impossible.

Lasso MCP Gateway directly mitigates these vulnerabilities, allowing teams to define policies, monitor security risks in real-time, block attacks before they happen, and enable the open source community to prepare enterprise readiness for MCP adoption.

About Lasso
Lasso is at the forefront of GenAI security, delivering cutting-edge solutions that protect GenAI applications from emerging threats. With a focus on governance, observability, and seamless integration, Lasso empowers organizations to securely navigate the GenAI era. Lasso was recently named 2024 Gartner® Cool Vendors™ for AI Security. For more information about Lasso Security's suite of GenAI Security solutions, visit www.lasso.security.

View source version on businesswire.com: https://www.businesswire.com/news/home/20250417840621/en/