Read a KV secret from HashiCorp Vault at the specified path and mount point
AI agents call vault_kv_read to retrieve information from HashiCorp Vault MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves secrets from Vault without modifying, deleting, or executing operations. However, severity is medium rather than low because: (1) secrets retrieved could be sensitive credentials (API keys, passwords, tokens) that an agent could misuse or exfiltrate, and (2) unauthorized secret access could compromise downstream systems.
From the tool's definition Tool name is 'vault_kv_read' and description states 'Read a KV secret from HashiCorp Vault at the specified path'. The verb 'read' and the absence of any write, delete, or execute operations indicate retrieval-only functionality with no side effects.
Attacks that exploit this kind of access
Read a KV secret from HashiCorp Vault at the specified path and mount point. It is categorised as a Read tool in the HashiCorp Vault MCP Server MCP Server, which means it retrieves data without modifying state.
Register the HashiCorp Vault MCP Server MCP server in PolicyLayer and add a rule for vault_kv_read: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches HashiCorp Vault MCP Server. Nothing to install.
vault_kv_read is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the vault_kv_read rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for vault_kv_read. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
vault_kv_read is provided by the HashiCorp Vault MCP Server MCP server (rod-anami-kyndryl/hashi-vault-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →