AI agents use upsert to create or update resources in Pgmcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pgmcp environment.
Upsert is inherently a Write operation—it either inserts new data or updates existing records reversibly. While the empty description lowers confidence slightly, the context (PostgreSQL admin server) and sibling tools (create_or_replace_function, delete, destroy_corpus) make the Write categorization clear.
From the tool's definition Tool named 'upsert' with empty description on a PostgreSQL administration server alongside tools like 'create_or_replace_function', 'create_job', and 'delete'. Upsert is a standard database operation that creates or modifies records.
Attacks that exploit this kind of access
upsert. It is categorised as a Write tool in the Pgmcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pg MCP server in PolicyLayer and add a rule for upsert: 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 Pgmcp. Nothing to install.
upsert 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 upsert 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 upsert. 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.
upsert is provided by the Pg MCP server (veloper/pgmcp). 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 →