Export all graph nodes and edges to a timestamped JSONL backup file in the backups/ directory.
AI agents call graph_export to retrieve information from Graph-Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads the entire graph database and writes it to a backup file. While it does create a file on disk (a Write-like side effect), its primary purpose is data export/backup rather than modifying the graph itself. The most significant risk is data exfiltration — the entire knowledge graph (which may contain sensitive personal information) is dumped to a file.
From the tool's definition Export all graph nodes and edges to a timestamped JSONL backup file in the backups/ directory.
Attacks that exploit this kind of access
Export all graph nodes and edges to a timestamped JSONL backup file in the backups/ directory. It is categorised as a Read tool in the Graph-Memory MCP Server, which means it retrieves data without modifying state.
Register the Graph-Memory MCP server in PolicyLayer and add a rule for graph_export: 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 Graph-Memory. Nothing to install.
graph_export 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_export 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_export. 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_export is provided by the Graph-Memory MCP server (stevepridemore/graph-memory). 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 →