AI agents use save_database to create or update resources in Re — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Re environment.
The tool creates or overwrites a database file on disk. While the operation itself is reversible (can be undone by restoring from backup or reloading a prior version), it commits in-memory changes to persistent storage.
From the tool's definition save_database saves/persists the current database to disk, a reversible write operation that modifies stored data.
Attacks that exploit this kind of access
Save the current database to disk (may take minutes for large DBs). It is categorised as a Write tool in the Re MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Re MCP server in PolicyLayer and add a rule for save_database: 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 Re. Nothing to install.
save_database is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the save_database 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 save_database. 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.
save_database is provided by the Re MCP server (jtsylve/re-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 →