AI agents use json_insert to create or update resources in Postgres Mcp Legacy — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Postgres Mcp Legacy environment.
This tool performs INSERT or UPDATE operations on JSONB columns in PostgreSQL. While these are reversible (via transaction rollback or subsequent updates), they modify persistent data. The 'high' severity reflects that an agent could modify critical business data if pointed at production databases.
From the tool's definition Tool description explicitly states 'Insert or update JSONB data' — these are write operations that modify data reversibly. The tool name 'json_insert' and description confirm it creates or modifies data without deletion.
Documented attack patterns abuse exactly the kind of access json_insert gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Postgres Mcp Legacy, and nothing reaches the server without passing your rules. This is the rule we recommend for json_insert:
{
"version": "1",
"default": "deny",
"tools": {
"json_insert": {
"limits": [
{
"counter": "json_insert_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} json_insert 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.
Free to start. No card required.
Insert or update JSONB data with validation. It is categorised as a Write tool in the Postgres Mcp Legacy MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Postgres Mcp Legacy MCP server in PolicyLayer and add a rule for json_insert: 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 Mcp Legacy. Nothing to install.
json_insert 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 json_insert 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 json_insert. 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.
json_insert is provided by the Postgres Mcp Legacy MCP server (neverinfamous/postgres-mcp-legacy). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Postgres Mcp Legacy, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
60 Postgres Mcp Legacy tools catalogued and risk-classified — across an index of 43,000+ MCP servers.