Retrieve the current GC debug flags from the CDV server.
AI agents call get_gc_stats to retrieve information from Cloudera Data Visualization MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool fetches GC (garbage collection) statistics and debug flag information from the server. This is a read-only operation that has no impact on system state, data integrity, or resources. It poses minimal risk as it only gathers diagnostic information.
From the tool's definition 'Retrieve the current GC debug flags from the CDV server' — this is a query operation that retrieves existing data without modification or side effects.
Attacks that exploit this kind of access
Retrieve the current GC debug flags from the CDV server. It is categorised as a Read tool in the Cloudera Data Visualization MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Cloudera Data Visualization MCP Server MCP server in PolicyLayer and add a rule for get_gc_stats: 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 Cloudera Data Visualization MCP Server. Nothing to install.
get_gc_stats 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 get_gc_stats 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 get_gc_stats. 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.
get_gc_stats is provided by the Cloudera Data Visualization MCP Server MCP server (kevintalbert/cdv-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 →