Salt Security, a leading name in AI agent and API security, has unveiled its groundbreaking Salt MCP Finder technology positioned as the industry’s first dedicated discovery engine for Model Context Protocol (MCP) servers. As MCP servers rapidly expand across enterprises to power agentic AI, this tool aims to give organizations a clear, authoritative view of their entire MCP landscape, even as these servers often emerge without IT or security oversight.
As companies accelerate their adoption of agentic AI, MCP servers are quickly becoming the invisible backbone of this ecosystem. These servers act as universal API brokers, enabling AI agents to take actions such as pulling data, triggering tools, executing workflows, and integrating with internal systems. However, this newfound capability also introduces a looming security concern: MCP servers are being deployed at a rapid pace and frequently without proper governance.
AI Authority Trend: DHL Boosts Operational Efficiency and Customer Communications with HappyRobot’s AI Agents
Developers, business units, vendors, contractors, and even open-source contributors are spinning up MCP servers for various use cases from rapid prototyping to enabling SaaS integrations. Moreover, internal teams often deploy MCP servers alongside new internal APIs to support shadow agentic workflows, leaving critical components outside the purview of IT and security teams. Consequently, a fragmented API governance environment amplifies risk and creates blind spots across the enterprise.
This uncontrolled growth leads to an expanding network of AI-connected infrastructure that is nearly invisible to central security teams. Organizations often lack visibility into crucial details, including how many MCP servers exist, who controls them, what data they expose, and whether required security controls like authentication, authorization, and logging are in place. Recent industry findings highlight the urgency: within ten months of MCP’s introduction, Fortune 500 companies collectively deployed more than 16,000 MCP servers. Additionally, one scan of 1,000 MCP servers revealed that 33% contained critical vulnerabilities, with each server averaging more than five.
Gartner reinforces this warning, noting that, “Most tech providers remain unprepared for the surge in agent-driven API usage. Gartner predicts that by 2028, 80% of organizations will see AI agents consume the majority of their APIs, rather than human developers.” Another Gartner insight adds, “As agentic AI transforms enterprise systems, tech CEOs who understand and implement MCP would drive growth, ensure responsible deployment and secure a competitive edge MCP is foundational for secure, efficient collaboration among autonomous agents, directly addressing trust, security, and cost challenges.”
AI Authority Trend: Kore.ai Partners with Microsoft to Launch AI Agents in Microsoft 365
Addressing this visibility gap, Salt’s MCP Finder technology tackles the foundational requirement for governing the AI Action Layer organizations must first understand the attack surface. As Nick Rago, VP of Product Strategy at Salt Security, emphasized, “You can’t secure what you can’t see. Every MCP server is a potential action point for an autonomous agent. Our MCP Finder technology gives CISOs the single source of truth they need to finally answer the most important question in agentic AI: What can my AI agents do inside my enterprise?”
To deliver this visibility, Salt MCP Finder consolidates discovery into a single authoritative registry through three intelligent layers:
- External Discovery – Salt Surface:
Identifies publicly exposed MCP servers, including abandoned, misconfigured, or unknown deployments. - Code Discovery – GitHub Connect:
Examines private repositories to detect MCP-related APIs, definitions, shadow integrations, and blueprint files before deployment. - Runtime Discovery – Agentic AI Behavior Mapping:
Analyzes live agent traffic to reveal active MCP servers, invoked tools, and data flow patterns.
By unifying these discovery streams, Salt equips enterprises with a complete MCP inventory, enabling them to visualize risks, enforce governance, and extend AI safety policies beyond the model directly into the action layer where real decisions and workflows occur.
AI Authority Trend: AlertD Launches AI Agentic SRE and DevOps Platform to Transform Cloud Operations
To share your insights, please write to us at info@intentamplify.com
