List databases on a specific CCX datastore
AI agents call ccx_list_databases to retrieve information from Severalnines CCX 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 and enumerates databases on a datastore without modifying, deleting, or executing anything. It is a read-only operation with minimal blast radius if misused—an AI agent can only view existing database information, not alter system state.
From the tool's definition Tool name 'ccx_list_databases' and description 'List databases on a specific CCX datastore' indicate a query/retrieval operation with no side effects.
Attacks that exploit this kind of access
List databases on a specific CCX datastore. It is categorised as a Read tool in the Severalnines CCX MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Severalnines CCX MCP Server MCP server in PolicyLayer and add a rule for ccx_list_databases: 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 Severalnines CCX MCP Server. Nothing to install.
ccx_list_databases 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 ccx_list_databases 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 ccx_list_databases. 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.
ccx_list_databases is provided by the Severalnines CCX MCP Server MCP server (severalnines/ccx-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 →