AI agents call entire_dispatch to retrieve information from Entire without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries checkpoint/session data to produce a summary report. This is a retrieval operation (Read) with minimal blast radius—misuse would only expose existing agent work history, not modify systems or execute arbitrary code. The tool fits the Read category: 'retrieves or queries data; no side effects'.
From the tool's definition The tool 'entire_dispatch' is described as 'Generate a dispatch summarizing recent agent work.' It reads/retrieves data about recent agent activity and generates a summary.
Attacks that exploit this kind of access
Generate a dispatch summarizing recent agent work. Uses \. It is categorised as a Read tool in the Entire MCP Server, which means it retrieves data without modifying state.
Register the Entire MCP server in PolicyLayer and add a rule for entire_dispatch: 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 Entire. Nothing to install.
entire_dispatch 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 entire_dispatch 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 entire_dispatch. 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.
entire_dispatch is provided by the Entire MCP server (jurislm/entire-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →