Preview the effect of INSERT/UPDATE/DELETE without executing. Shows estimated rows affected and sample of rows that would be modified. Use this before running destructive queries to verify the impact. Optionally use server/database/schema params for one-time execution on a different server.
AI agents call mutation_preview to retrieve information from Postgres without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool explicitly does NOT execute mutations — it only previews/simulates them. It reads and analyzes what would happen, returning estimated row counts and samples. No data is modified, making this a Read operation. Severity is low since it only reads data to provide impact estimates.
From the tool's definition Preview the effect of INSERT/UPDATE/DELETE without executing. Shows estimated rows affected and sample of rows that would be modified.
Attacks that exploit this kind of access
Preview the effect of INSERT/UPDATE/DELETE without executing. Shows estimated rows affected and sample of rows that would be modified. Use this before running destructive queries to verify the impact. Optionally use server/database/schema params for one-time execution on a different server. It is categorised as a Read tool in the Postgres MCP Server, which means it retrieves data without modifying state.
Register the Postgres MCP server in PolicyLayer and add a rule for mutation_preview: 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.
mutation_preview is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the mutation_preview 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 mutation_preview. 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.
mutation_preview 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.
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 →