AI agents call format_code to retrieve information from Deobfuscate MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Formatting code with Prettier is a read/transform operation that takes input code and returns formatted output. It does not persist changes, execute arbitrary code, delete data, or involve financial operations. The tool purely processes and returns reformatted text, making it a low-severity read/transform operation.
From the tool's definition Formats code with Prettier
Documented attack patterns abuse exactly the kind of access format_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Deobfuscate MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for format_code:
{
"version": "1",
"default": "deny",
"tools": {
"format_code": {}
}
}format_code is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Formats code with Prettier. It is categorised as a Read tool in the Deobfuscate MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Deobfuscate MCP Server MCP server in PolicyLayer and add a rule for format_code: 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 Deobfuscate MCP Server. Nothing to install.
format_code 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 format_code 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 format_code. 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.
format_code is provided by the Deobfuscate MCP Server MCP server (madebytokens/deobfuscate-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Deobfuscate MCP Server, 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.
10 Deobfuscate MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.