Normalize Python-style JSON to valid JSON format
AI agents invoke json_normalize to trigger actions in Postgres Mcp Legacy. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool performs data transformation (converting Python-style JSON, e.g., with single quotes, True/False/None, to valid JSON). This involves executing code/logic to parse and reformat input. It is not a simple read (it transforms), not a write (no persistent storage implied), and not destructive. Execute is most appropriate as it runs a transformation process.
From the tool's definition 'Normalize Python-style JSON to valid JSON format' — implies processing/transforming input data, potentially executing parsing or conversion logic
Documented attack patterns abuse exactly the kind of access json_normalize 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_normalize:
{
"version": "1",
"default": "deny",
"tools": {
"json_normalize": {
"limits": [
{
"counter": "json_normalize_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}json_normalize stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Normalize Python-style JSON to valid JSON format. It is categorised as a Execute tool in the Postgres Mcp Legacy MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Postgres Mcp Legacy MCP server in PolicyLayer and add a rule for json_normalize: 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_normalize is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the json_normalize 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_normalize. 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_normalize 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.