Adds a new column to a table dynamically.
AI agents use add_column 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.
Adding a column to a table modifies the database schema in a reversible manner—columns can be dropped or altered later. This is a Write operation (creates/modifies data structure) rather than Execute (which would apply to arbitrary SQL execution like run_sql) or Destructive (which would apply to irreversible deletions).
From the tool's definition Tool name is 'add_column' and description states it 'Adds a new column to a table dynamically.' This is a schema modification operation that creates new database structure.
Attacks that exploit this kind of access
Adds a new column to a table dynamically. 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 add_column: 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.
add_column 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 add_column 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 add_column. 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.
add_column 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 →