Creates a backup of the Firebird database
AI agents use backup-database to create or update resources in MCP Firebird — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Firebird environment.
Creating a backup is a Write operation: it generates a new file or artifact (the backup) but does not alter or destroy the source database. It is not Destructive (source data is preserved), not Execute (no arbitrary code runs), and not Financial. Severity is medium because misuse could expose sensitive database contents or consume significant storage/resources, but the source database remains intact.
From the tool's definition 'Creates a backup of the Firebird database' — this is a read/copy operation that produces a new backup artifact without modifying or deleting existing data.
Attacks that exploit this kind of access
Creates a backup of the Firebird database. It is categorised as a Write tool in the MCP Firebird MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Firebird 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 Firebird. 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 Firebird MCP server (luancamara/mcpfirebird). 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 →