Read a secret from Vault at the specified path
AI agents call vault_read to retrieve information from 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 creating, modifying, or deleting data. However, severity is elevated to 'medium' rather than 'low' because unauthorized access to secrets could expose sensitive credentials, API keys, database passwords, or other confidential data that an AI agent should not read without proper authorization context.
From the tool's definition Tool name 'vault_read' and description 'Read a secret from Vault at the specified path' explicitly indicate data retrieval with no modification.
Attacks that exploit this kind of access
Read a secret from Vault at the specified path. It is categorised as a Read tool in the Vault MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Vault MCP Server MCP server in PolicyLayer and add a rule for vault_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 Vault MCP Server. Nothing to install.
vault_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_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_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_read is provided by the Vault MCP Server MCP server (kelleyblackmore/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 →