Delinea launches free MCP Server to secure AI agent credentials
Delinea has made its open-source Model Context Protocol MCP Server available for free on GitHub to help secure AI agent credentials in the workplace.
AI agents are increasingly used in workplaces, but granting them access to sensitive systems poses security risks. Credentials are often stored in plain text, embedded in prompts, or shared without proper oversight. Delinea addresses this issue with its new open-source Model Context Protocol (MCP) Server, now available for free on GitHub.
How the MCP Server Works
The MCP Server acts as a secure intermediary between AI agents and the Delinea Platform, enabling them to retrieve and use credentials safely. It enforces identity checks and policy rules to track and limit access, eliminating the need for custom integrations across tools or workflows.
Phil Calvin, Delinea's Chief Product Officer, emphasized the server's design to minimize credential misuse by AI systems. "Delinea MCP Server combines abstraction, least-privilege controls, and ephemeral authentication to ensure AI tools remain productive without creating vulnerabilities for credential leakage or misuse," he told Help Net Security.
The server exposes only predefined functions, allowing AI tools to request necessary access without handling raw credentials. Policies, scope controls, and short-lived tokens further restrict access, keeping sensitive passwords out of AI agents' direct reach.
The Importance of Securing AI Credentials
Many AI agents interact with databases or cloud services, often relying on hardcoded credentials—posing audit and revocation challenges. The MCP Server mitigates these risks through ephemeral tokens and centralized policies. It supports OAuth and integrates with platforms like ChatGPT and Claude.
Deployment Challenges and Support
Integrating the MCP Server into existing AI workflows requires careful planning. "It’s not plug-and-play," Calvin noted. "Organizations must address configuration, credential handling, and ensuring AI agents adopt the new tools without bypassing them."
Delinea simplifies adoption with:
- Docker images for easy deployment
- Comprehensive documentation
- Sample integrations for tools like ChatGPT, Claude, and VSCode Copilot
- Best practices for scoping tools and testing deployments
Related News
CometJacking Attack Hijacks Perplexity AI Browser to Steal User Data
A malicious URL exploit turns Perplexity's Comet AI browser into a data thief, exfiltrating emails, calendar, and memory via encoded payloads.
Zero Trust Auditing Essential for AI Era Cybersecurity
Exploring how Zero Trust Auditing is redefining enterprise assurance in the AI era by continuously verifying trust across devices, networks, and AI systems.
About the Author
Dr. Lisa Kim
AI Ethics Researcher
Leading expert in AI ethics and responsible AI development with 13 years of research experience. Former member of Microsoft AI Ethics Committee, now provides consulting for multiple international AI governance organizations. Regularly contributes AI ethics articles to top-tier journals like Nature and Science.