Vault Radar MCP server overview

The Vault Radar model context protocol (MCP) server helps improve agentic workflows related to Vault Radar. The server requests information directly from the HCP platform so that your model can formulate intelligent responses.

Beta feature

This feature is currently available as beta. The beta functionality is stable but possibly incomplete and subject to change. We strongly discourage using beta features in production.

Introduction

MCP standardizes how AI models can discover and interact with external tools, applications, and data sources. You can configure MCP clients, such as an AI or LLM chat, to send requests through an MCP server. The model can then give answers to prompts that it may not be trained on. Refer to the MCP documentation for details about how MCP works.

You can configure your AI model to connect to the Vault Radar MCP server so that it can request information about data sources, resources, and found events from the HCP Vault Radar APIs.

Workflow

Vault Radar MCP server tools

The Vault Radar MCP server runs as a container on your local workstation and exposes functionality to your clients. The Vault Radar MCP server includes a set of tools that retrieve different types of information from your project's HCP Vault Radar instance:

query_vault_radar_data_sources: Queries all data sources available in the Vault Radar project.
query_vault_radar_resources: Queries all resources in your HCP Vault Radar project.
query_vault_radar_events: Queries all the events in your HCP Vault Radar project.
list_vault_radar_secret_types: Lists the detected secret types in your HCP Vault Radar project.

Changelog

See the changelog for the Vault Radar MCP server to keep track of changes and updates.

Next steps

Deploy the Vault Radar MCP server and integrate it with your local AI client.