AI agents call kobold_perf_info to retrieve information from Kobold MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a diagnostic/monitoring tool that retrieves system performance statistics. Retrieving performance data has no side effects, does not trigger external operations, and does not modify or delete any data. It falls clearly into the Read category with low severity due to minimal risk from misuse.
From the tool's definition Tool name 'kobold_perf_info' and description 'Get performance information' indicate data retrieval with no side effects. The tool queries performance metrics rather than modifying, executing, or deleting anything.
Documented attack patterns abuse exactly the kind of access kobold_perf_info gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kobold MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for kobold_perf_info:
{
"version": "1",
"default": "deny",
"tools": {
"kobold_perf_info": {}
}
}kobold_perf_info 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.
Get performance information. It is categorised as a Read tool in the Kobold MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Kobold MCP Server MCP server in PolicyLayer and add a rule for kobold_perf_info: 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 Kobold MCP Server. Nothing to install.
kobold_perf_info 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 kobold_perf_info 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 kobold_perf_info. 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.
kobold_perf_info is provided by the Kobold MCP Server MCP server (phialsbasement/koboldcpp-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kobold 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.
20 Kobold MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.