BMClogo

Delinea is released Model Context Protocol (MCP) Server This allows Ai-Agent to access credentials stored in Delinea Secret Server and Delinea platforms. The server applies identity checking and policy rules on every call, aiming to put long-term secrets out of proxy memory

What new features are there for me?

Github Project DelineaXPM/delinea-mcp (MIT License) exposes a constrained MCP tool surface for credential retrieval and account operations, supports OAUTH 2.0 dynamic client registration according to MCP specifications, and provides STDIO and HTTP/SSE shipping. Repo includes editor/agent integration Docker artifacts and sample configurations

How it works?

This server exposes the MCP tool for proxying secret servers, as well as (options) Delinea platform: Secret and folder retrieval/search, inbox/access-access assistant, user/session admin and report execution; the secret itself is still vaulted and never presented to the agent. The configuration separates secrets into environment variables (e.g. DELINEA_PASSWORD) and non-secret config.jsonwith scope control (enabled_toolsallow object types), TLS certificates and optionally registered pre-shared keys.

Explain to me why this is crucial to me

Enterprises are quickly connected to the operating system through MCP. Recent events (such as emails that completely release the Rogue MCP package) are unable to require registration controls, TLS, minimal change edge tool surfaces and traceable identity contexts on every call. Delinea’s server claims to implement these controls in PAM alignment mode (temporary verification + policy check + audit), reducing credential spread and simplifying revocation.

Summary

Delinea’s MIT licensed MCP servers provide businesses with a standard, auditable way to use AI-Antertential corverental Access (Short Lives lives lives lives lives lives lives lives lives lives lives nive cresituation and Condended tool) to reduce the secret risks of integration with Secret Server and Delinea platforms. Now available Girubwith initial coverage and technical details, confirms OAuth2, STDIO/HTTP (SSE) shipping and range operations.


Michal Sutter is a data science professional with a master’s degree in data science from the University of Padua. With a solid foundation in statistical analysis, machine learning, and data engineering, Michal excels in transforming complex data sets into actionable insights.

🔥 (Recommended Reading) NVIDIA AI Open Source VIPE (Video Pose Engine): a powerful and universal 3D video annotation tool for spatial AI

Source link