Reset config.json to defaults from config.default.json (manual reset - overwrites current config)
AI agents call reset_config to permanently remove resources in Agent Knowledge MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly replaces the active configuration file with defaults, destroying any customizations or settings made since installation. While the default config file presumably exists as a backup source, the current config is overwritten and cannot be recovered through the tool itself. This qualifies as destructive because the action cannot be easily undone without external backups.
From the tool's definition Overwrites current config without restore option; description explicitly states it 'overwrites current config'
Documented attack patterns abuse exactly the kind of access reset_config gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Agent Knowledge MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for reset_config:
{
"version": "1",
"default": "deny",
"hide": [
"reset_config"
]
} reset_config disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Reset config.json to defaults from config.default.json (manual reset - overwrites current config). It is categorised as a Destructive tool in the Agent Knowledge MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Agent Knowledge MCP server in PolicyLayer and add a rule for reset_config: 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 Agent Knowledge MCP. Nothing to install.
reset_config is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the reset_config 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 reset_config. 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.
reset_config is provided by the Agent Knowledge MCP server (itshare4u/agentknowledgemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Agent Knowledge MCP, 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.
27 Agent Knowledge MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.