pki-read-root-ca
AI agents call pki-read-root-ca to retrieve information from Vault MCP Server (mschuchard) without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves PKI root CA information without modifying it (no side effects). However, severity is elevated to 'high' because root CA material is sensitive cryptographic data—if exposed to an untrusted agent, it could compromise the entire PKI infrastructure's secrecy and trust chain, even though the operation itself is read-only.
From the tool's definition Tool name 'pki-read-root-ca' indicates reading PKI root CA certificate/configuration. Description is empty, but context from server description shows it's part of Vault's PKI secret engine management.
Attacks that exploit this kind of access
pki-read-root-ca. It is categorised as a Read tool in the Vault MCP Server (mschuchard) MCP Server, which means it retrieves data without modifying state.
Register the Vault MCP Server (mschuchard) MCP server in PolicyLayer and add a rule for pki-read-root-ca: 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 (mschuchard). Nothing to install.
pki-read-root-ca 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 pki-read-root-ca 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 pki-read-root-ca. 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.
pki-read-root-ca is provided by the Vault MCP Server (mschuchard) MCP server (mschuchard/vault-mcp-server). 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 →