AI agents call graph_stats to retrieve information from Graphdb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries and returns summary statistics about the indexed Rails codebase graph. It performs a read-only retrieval of internal state metrics. No code execution, data modification, deletion, or financial impact is possible. The low severity reflects that misuse of this tool by an AI agent would have minimal negative consequences—it only exposes counts and health metrics of the graph database itself.
From the tool's definition Tool returns 'Counts of nodes/edges by kind — quick health check.' This is a statistics/introspection operation that retrieves aggregated metadata about the graph structure with no data modification, parameter-driven execution risk, or side effects.
Attacks that exploit this kind of access
Counts of nodes/edges by kind — quick health check. It is categorised as a Read tool in the Graphdb MCP Server, which means it retrieves data without modifying state.
Register the Graphdb MCP server in PolicyLayer and add a rule for graph_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 Graphdb. Nothing to install.
graph_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 graph_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 graph_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.
graph_stats is provided by the Graphdb MCP server (samagra001/claude-code-graphdb). 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 →