Highflame and Tailscale Partner to Secure AI Agents and Model & MCP Interactions at the Network Layer

Integration brings real-time security evaluation to LLM & MCP interactions without requiring changes to agents or developer workflows

Apr. 3, 2026 at 4:06pm by Ben Kaplan

Got story updates? Submit your updates here. ›

A highly detailed, glowing 3D illustration of a complex network of interconnected cybernetic hardware components, with pulsing neon cyan and magenta lights illuminating the intricate circuitry and data pathways, conceptually representing the advanced, high-tech infrastructure powering AI systems and their interactions.Securing the invisible infrastructure powering AI's expanding reach across the enterprise.San Francisco Today

AI agents now generate thousands of LLM requests across developer machines, CI pipelines, and internal systems, creating a new and largely unmonitored security surface for enterprises. Highflame, an AI Security company, has partnered with Tailscale to bring real-time security evaluation to AI activity at the network layer. The integration allows organizations to continuously evaluate AI activity, enforce security policies, and maintain visibility into how AI systems operate, without requiring changes to agents or developer workflows.

Why it matters

As AI agents become more prevalent across enterprises, the security risks associated with their interactions have grown. This partnership between Highflame and Tailscale aims to address this issue by providing a unified layer of visibility and control across both the agent and network layers, allowing organizations to better monitor and secure their AI systems.

The details

The integration between Highflame and Aperture by Tailscale allows organizations to gain visibility into LLM interactions and assess risk across prompts, tool usage, and model outputs. Aperture by Tailscale provides a centralized gateway for AI traffic, routing requests through the network and capturing usage, identity, and telemetry. Highflame then analyzes each interaction to detect risks, including prompt injection, secret/credentials/PII leakage, unsafe tool execution, and policy violations.

  • The integration is currently in alpha and available to early users.

The players

Highflame

An AI Security company focused on securing AI agents and their interactions.

Tailscale

A company that provides secure, identity-first networking, simplifying complex network setups with fast, reliable connections that seamlessly scale across cloud and on-premises environments.

Aperture by Tailscale

A centralized gateway for AI traffic that routes requests through the network and captures usage, identity, and telemetry.

Sharath Rajasekar

CEO of Highflame.

Avery Pennarun

CEO of Tailscale.

Got photos? Submit your photos here. ›

What they’re saying

“AI agents are already operating across every layer of the enterprise, but security hasn't caught up to where the activity actually happens.”

— Sharath Rajasekar, CEO of Highflame

“Aperture gives organizations a reliable control point for AI traffic. With Highflame, customers can take that further by understanding the security implications across prompts, tool calls, and model responses, turning visibility into something they can actually use.”

— Avery Pennarun, CEO of Tailscale

What’s next

Aperture by Tailscale is currently in alpha and available to early users. Organizations using Aperture can enable the Highflame integration with minimal configuration.

The takeaway

This partnership between Highflame and Tailscale aims to address the growing security risks associated with AI agents by providing a unified layer of visibility and control across both the agent and network layers. This allows organizations to continuously evaluate AI activity, enforce security policies, and maintain visibility into how AI systems operate, without requiring changes to agents or developer workflows.