TLDR: Delinea has released a free, open-source Model Context Protocol (MCP) Server designed to enhance the security of AI agents. This server acts as a secure intermediary, providing AI agents with controlled access to credentials, enforcing policy rules, and ensuring compliance, thereby mitigating risks associated with direct credential exposure in AI-driven workflows.
SAN FRANCISCO – September 23, 2025 – Delinea, a leading provider of solutions for securing human and machine identities, has announced the launch of its free, open-source Model Context Protocol (MCP) Server. This new offering, now available on GitHub, aims to address the growing security challenges associated with integrating Artificial Intelligence (AI) agents into enterprise workflows.
As AI agents become increasingly prevalent in software development and IT operations, organizations face significant risks when granting these agents access to sensitive systems and data. Traditional methods often involve embedding credentials directly into large language model (LLM) prompts or building complex custom API integrations, both of which can lead to credential leakage, misuse, and a lack of auditability. Delinea’s MCP Server is designed to circumvent these vulnerabilities by acting as a secure intermediary between AI agents and the Delinea Platform.
Phil Calvin, Chief Product Officer at Delinea, emphasized the server’s core mission: “AI agents are revolutionizing innovation, but they also introduce security and compliance challenges. To mitigate risks like access request hallucinations and vibe hacking, it’s crucial to enforce identity context at every interaction. MCP Server ensures AI agents operate within secure boundaries, using ephemeral tokens and policy checks to help maintain traceability and protect credentials.”
The Delinea MCP Server connects AI agents to the Delinea Platform, enabling them to securely retrieve and utilize credentials without ever directly handling raw passwords. The server applies stringent identity checks and policy rules, ensuring that all access is tracked, limited, and auditable. This approach significantly reduces the risk of credential misuse and enhances compliance with regulatory frameworks.
Key benefits of the Delinea MCP Server include:
Reduced Risk: It prevents AI agents from gaining unrestricted access to sensitive data, protecting credentials and ensuring all actions are auditable.
Improved Productivity: By eliminating the need for custom connectors, the server streamlines integration processes, leading to faster time-to-value and reduced engineering overhead.
Enhanced Compliance: The enforcement of identity context, privilege, and policy checks at every interaction ensures full traceability and auditability, crucial for adhering to compliance standards.
Also Read:
- Airia Unveils Secure MCP Gateway to Fortify Enterprise AI Deployments
- Infinitus Unveils Model Context Protocol Server to Advance AI Interoperability in Healthcare
The MCP Server is compatible with leading vendors and supports open standards such as OAuth for seamless integration. Delinea also provides experimental connectors for popular AI platforms like ChatGPT and Claude, offering organizations flexibility as the AI ecosystem continues to evolve. This open-source release marks Delinea’s first official open-source package, empowering developers to integrate robust MCP capabilities into their custom AI agents for a safer and more scalable AI-driven future.
