Get database file size and row counts for all tables.
AI agents call db_get_stats to retrieve information from Overlord 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 informational statistics about the database (file size, row counts) without creating, modifying, or deleting any data. It has no side effects and falls clearly into the Read category. Severity is low because the information exposed is non-sensitive operational metadata that does not directly enable harmful actions even if misused by an AI agent.
From the tool's definition Tool name 'db_get_stats' and description 'Get database file size and row counts for all tables' indicate retrieval of database metadata and statistics without modification or deletion of data.
Attacks that exploit this kind of access
Get database file size and row counts for all tables. It is categorised as a Read tool in the Overlord MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Overlord MCP Server MCP server in PolicyLayer and add a rule for db_get_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 Overlord MCP Server. Nothing to install.
db_get_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 db_get_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 db_get_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.
db_get_stats is provided by the Overlord MCP Server MCP server (skeeminator/overlord-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 →