AI agents call kobold_token_count 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 tool performs a stateless read-only operation: it analyzes input text and returns a numeric count. There are no side effects, no data modification, no code execution, and no destructive actions. It is information retrieval only, making it a Read category risk. Severity is low because misuse (e.g., profiling input length) poses minimal security risk compared to other tool categories.
From the tool's definition Tool name is 'kobold_token_count' and description states 'Count tokens in text' — a pure query operation that retrieves token count information without modifying, deleting, or executing any external operations.
Documented attack patterns abuse exactly the kind of access kobold_token_count 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_token_count:
{
"version": "1",
"default": "deny",
"tools": {
"kobold_token_count": {}
}
}kobold_token_count 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.
Count tokens in text. 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_token_count: 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_token_count 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_token_count 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_token_count. 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_token_count 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.