New integration with Claude’s Compliance API gives security teams a live, read-only inventory of the MCP servers connected to their Claude organization
PALO ALTO, Calif., Sept. 29, 2026 /PRNewswire/ — Salt Security, the leader in agentic and API security, today introduced Salt Claude Connect, an integration that gives security teams continuous, read-only visibility into the Model Context Protocol (MCP) servers connected to their Claude Enterprise organization. The integration works with Claude’s Compliance API to surface the organization-managed MCP servers in a security team’s Salt inventory, including when each was added, updated, or removed, and its current status.
As enterprises adopt AI, security and IT teams face a foundational question: what is connected to our AI, and what can it access? MCP servers extend what an AI environment can reach, and in a large organization, they can be added faster than security can track them. The scale of the exposure is already measurable: Trend Micro research found the number of MCP servers exposed on the public internet with no authentication or encryption nearly tripled to 1,467 in a matter of months, with the majority hosted on major cloud providers and offering direct read access to the data behind them. Without a current inventory, teams cannot answer basic questions about their AI attack surface, govern what is connected, or investigate when something changes.
What Salt Claude Connect provides
Salt Claude Connect reads an organization’s activity feed through Claude’s Compliance API and automatically surfaces the organization-managed MCP servers in the Salt AI inventory. Security teams get a live, always-current picture of which MCP servers are connected to their Claude organization, when they were added or removed, and their current status. Discovered servers appear in the Salt Agentic inventory labeled by source, each showing server name, status, and the time of its most recent lifecycle event, and the inventory updates continuously as connectors are added, updated, or removed.
Read-only and narrow by design
The integration is built around least-privilege access. It requires a single read-only scope and reads only MCP server lifecycle activity. It never sends prompts to Claude, and it never reads chat content, file content, or project data. The only information Salt stores is MCP server lifecycle events, and the integration never modifies the Claude organization in any way.
“MCP servers are one of the fastest-growing parts of the enterprise attack surface, and for most security teams, what’s connected to their AI environment has been a blind spot they couldn’t close,” said Roey Eliyahu, co-founder and CEO of Salt Security. “Salt Claude Connect turns that blind spot into a live inventory. Security teams can see the MCP servers connected to their Claude Enterprise organization, track them as they’re added, removed, or changed, and finally govern their AI environment with the same rigor they apply everywhere else, all without ever touching the prompts or content that run through it.”
Availability
Salt Claude Connect is available now to Salt Security customers with a Claude Enterprise organization. Setup requires a Compliance Access Key with a read-only scope and the organization’s ID, and takes a few steps from the Salt dashboard. Full details are available at salt.security.
About Salt Security
Salt Security is the leader in agentic and API security, protecting the world’s most innovative enterprises from AI agent and API attacks. AI is shifting from chatbots that answer to agents that act, and Salt secures the entire agentic path, from AI-generated code to runtime, across models, MCP servers, tools, and downstream APIs. Founded in 2016, Salt Security is backed by Sequoia Capital, S Capital, Tenaya Capital, Salesforce Ventures, Advent International, and other leading investors. For more information, visit salt.security.
Contact: Dr. Karl Bateson – [email protected]
SOURCE Salt Security
