Creates a new PostgreSQL database for a project.
AI agents use create_project_db to create or update resources in Pg Mnemosyne — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pg Mnemosyne environment.
Creating a new database is a reversible write operation—the database can be dropped if needed. However, it carries high severity because an AI agent could consume significant system resources (disk space, connection limits), interfere with other projects' infrastructure, or create databases with unintended names/purposes.
From the tool's definition Tool name 'create_project_db' combined with description 'Creates a new PostgreSQL database for a project' indicates database creation (write operation).
Attacks that exploit this kind of access
Creates a new PostgreSQL database for a project. It is categorised as a Write tool in the Pg Mnemosyne MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pg Mnemosyne MCP server in PolicyLayer and add a rule for create_project_db: 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 Pg Mnemosyne. Nothing to install.
create_project_db 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 create_project_db 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 create_project_db. 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.
create_project_db is provided by the Pg Mnemosyne MCP server (janadasroor/pg-mnemosyne-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 →