Create a backup of the current database to a file.
AI agents use backup_database to create or update resources in Mcp Csv Database — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Csv Database environment.
Backup operations create new data (the backup file) in a reversible manner. No data is modified, deleted, or destroyed. The backup itself can be ignored or deleted if needed. This is a Write operation with low severity since backups are defensive and cause no adverse effects when executed by an AI agent.
From the tool's definition Tool name 'backup_database' and description 'Create a backup of the current database to a file' indicate creation of a new backup file without modification or deletion of existing data.
Attacks that exploit this kind of access
Create a backup of the current database to a file. It is categorised as a Write tool in the Mcp Csv Database MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Csv Database MCP server in PolicyLayer and add a rule for backup_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 Mcp Csv Database. Nothing to install.
backup_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 backup_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 backup_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.
backup_database is provided by the Mcp Csv Database MCP server (lasitha-jayawardana/mcp-csv-database). 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 →