pki-read-urls
AI agents call pki-read-urls 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.
Despite the empty description lowering confidence slightly, the naming convention and context as a Vault administrative tool strongly suggest this reads PKI URL settings without side effects. No data modification, deletion, code execution, or financial operations are implied. This falls cleanly into the Read category.
From the tool's definition Tool name 'pki-read-urls' suggests a read operation on PKI (Public Key Infrastructure) URL configuration. The server description indicates it manages 'secret engines like KV v2, PKI, and Transit' and provides tools for 'system backend administration.' The…
Attacks that exploit this kind of access
pki-read-urls. 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-urls: 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-urls 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-urls 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-urls. 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-urls 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 →