generate_seed_data · Postgres MCP: Risk & Policy

WHAT IT DOES

What generate_seed_data does on Postgres

AI agents use generate_seed_data to create or update resources in Postgres — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Postgres environment.

WHY IT NEEDS A POLICY

Why generate_seed_data needs a policy

generate_seed_data creates and inserts new rows into a database table. This is a reversible Write operation—the generated data can be deleted if needed. It does not execute arbitrary code, does not permanently destroy existing data, and does not move money.

From the tool's definition The tool description states it will 'Generate schema-aware fake seed data for a table' and specifies behavior for inserting data (handling NOT NULL, UNIQUE/PK, enum types, defaults, text limits, and FK columns). This is a data creation operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

generate_seed_data Rate-limited

generate_seed_data stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "generate_seed_data": {
      "limits": [
        {
          "counter": "generate_seed_data_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Postgres, so you can run agents against it safely.

FAQ

Questions about generate_seed_data

What does the generate_seed_data tool do? +

Generate schema-aware fake seed data for a table. Respects NOT NULL, UNIQUE/PK (with retry-with-collision-suffix), enum types (cycles through labels), defaults (uses DEFAULT for unknown types), text length limits, and FK columns (skipped or filled — caller. It is categorised as a Write tool in the Postgres MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on generate_seed_data? +

Register the Postgres MCP server in PolicyLayer and add a rule for generate_seed_data: 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 Postgres. Nothing to install.

What risk level is generate_seed_data? +

generate_seed_data is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit generate_seed_data? +

Yes. Add a rate_limit block to the generate_seed_data 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.

How do I block generate_seed_data completely? +

Set action: deny in the PolicyLayer policy for generate_seed_data. 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.

What MCP server provides generate_seed_data? +

generate_seed_data is provided by the Postgres MCP server (teja-sudo/postgres-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.