AI agents call kobold_last_logprobs 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 retrieves log probabilities—debugging/analysis data from a previous text generation request. It performs no writes, deletions, code execution, or financial operations. Logprobs are metadata about token prediction confidence and pose minimal risk if disclosed or accessed. The tool fits the 'Read' category as it queries data without side effects.
From the tool's definition Tool name 'kobold_last_logprobs' and description 'Get token logprobs from the last request' indicate retrieval of metadata (log probabilities) from a completed generation operation.
Documented attack patterns abuse exactly the kind of access kobold_last_logprobs 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_last_logprobs:
{
"version": "1",
"default": "deny",
"tools": {
"kobold_last_logprobs": {}
}
}kobold_last_logprobs 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 token logprobs from the last request. 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_last_logprobs: 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_last_logprobs 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_last_logprobs 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_last_logprobs. 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_last_logprobs 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.