Explain why a chunk was omitted from a Context Receipt.
AI agents call explain_receipt_omission to retrieve information from Entroly Context Engine without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs information retrieval and analysis of existing Context Receipt data. It does not modify, delete, execute external operations, or commit financial transactions. The operation is purely informational—returning diagnostic or explanatory data about the compression/omission decisions made by the context engine. There is no mutation of state, no code execution, and no destructive action.
From the tool's definition The tool 'explain_receipt_omission' retrieves and explains information about why a chunk was omitted from a Context Receipt. The verb 'explain' and the purpose of querying/inspecting omission reasons indicate a read-only query operation with no side effects.
Documented attack patterns abuse exactly the kind of access explain_receipt_omission gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Entroly Context Engine, and nothing reaches the server without passing your rules. This is the rule we recommend for explain_receipt_omission:
{
"version": "1",
"default": "deny",
"tools": {
"explain_receipt_omission": {}
}
}explain_receipt_omission 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.
Explain why a chunk was omitted from a Context Receipt. It is categorised as a Read tool in the Entroly Context Engine MCP Server, which means it retrieves data without modifying state.
Register the Entroly Context Engine MCP server in PolicyLayer and add a rule for explain_receipt_omission: 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 Entroly Context Engine. Nothing to install.
explain_receipt_omission 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 explain_receipt_omission 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 explain_receipt_omission. 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.
explain_receipt_omission is provided by the Entroly Context Engine MCP server (juyterman1000/entroly). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Entroly Context Engine, 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.
52 Entroly Context Engine tools catalogued and risk-classified — across an index of 43,000+ MCP servers.