Saves table schemas (fields, types, relationships) to state.
AI agents use save_database_plan to create or update resources in Backend Architect MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Backend Architect MCP Server environment.
The tool modifies application state by persisting database schema definitions. While not directly destructive (schemas can be updated/overwritten), it is a Write operation that creates or modifies data reversibly within the project scaffold.
From the tool's definition Tool name 'save_database_plan' and description 'Saves table schemas (fields, types, relationships) to state' indicate persistent modification of application state representing database structure.
Attacks that exploit this kind of access
Saves table schemas (fields, types, relationships) to state. It is categorised as a Write tool in the Backend Architect MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Backend Architect MCP Server MCP server in PolicyLayer and add a rule for save_database_plan: 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 Backend Architect MCP Server. Nothing to install.
save_database_plan 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_plan 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_plan. 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_plan is provided by the Backend Architect MCP Server MCP server (jemhakdog/mcp_fastapi). 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 →