Get the current prompt manifest with version and hash.
AI agents call admin_get_prompt_manifest to retrieve information from CloudNativePG 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 metadata about the prompt manifest (version and hash) without side effects. It performs a read-only query of system configuration, making it a Read category tool. Severity is low because exposure of prompt manifest metadata presents minimal risk to system integrity or data security.
From the tool's definition Tool name 'admin_get_prompt_manifest' and description 'Get the current prompt manifest with version and hash' indicate a retrieval operation that queries existing configuration data without modification or execution of external operations.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Get the current prompt manifest with version and hash. It is categorised as a Read tool in the CloudNativePG MCP Server MCP Server, which means it retrieves data without modifying state.
Register the CloudNativePG MCP Server MCP server in PolicyLayer and add a rule for admin_get_prompt_manifest: 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 CloudNativePG MCP Server. Nothing to install.
admin_get_prompt_manifest 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 admin_get_prompt_manifest 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 admin_get_prompt_manifest. 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.
admin_get_prompt_manifest is provided by the CloudNativePG MCP Server MCP server (wateim/cnpg-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 →