util_log_loss
Log loss (cross-entropy) for a probability vs binary outcome
This record as markdown: /tools/io-github-davidmosiah-delx-protocol/util-log-loss.md
What util_log_loss does on Delx Protocol — Agent Recovery & Continuity
AI agents call util_log_loss to retrieve information from Delx Protocol — Agent Recovery & Continuity without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
prob | number | Yes | Input field: prob. |
outcome | integer | Yes | Input field: outcome. |
Parameters from the server's own tool schema.
Why util_log_loss is rated Low
Even though util_log_loss only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs util_log_loss safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Delx Protocol — Agent Recovery & Continuity, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For util_log_loss, this is the rule to start with:
util_log_loss is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Delx Protocol — Agent Recovery & Continuity, apply this rule, and every util_log_loss call is checked against it from then on.
Questions about util_log_loss
Log loss (cross-entropy) for a probability vs binary outcome. It is categorised as a Read tool in the Delx Protocol — Agent Recovery & Continuity MCP Server, which means it retrieves data without modifying state.
util_log_loss accepts 2 parameters: prob, outcome. Required: prob, outcome. The full parameter table on this page comes from the server's own tool schema.
Register the Delx Protocol — Agent Recovery & Continuity MCP server in PolicyLayer and add a rule for util_log_loss: 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 Delx Protocol — Agent Recovery & Continuity. Nothing to install.
util_log_loss 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 util_log_loss 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 util_log_loss. 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.
util_log_loss is provided by the Delx Protocol — Agent Recovery & Continuity MCP server (https://api.delx.ai/v1/mcp?src=registry). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Delx Protocol — Agent Recovery & Continuity, and thousands of servers like it.
Across the catalogue