AI agents call lattice_stats to retrieve information from Lattice without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query operation on document metadata/statistics. It retrieves information about a document that is already loaded into the Lattice engine but does not create, modify, delete, or execute arbitrary operations. The 'Get' verb and statistics-gathering purpose align with the Read category.
From the tool's definition Tool name 'lattice_stats' and description 'Get statistics about the currently loaded document' indicate a retrieval operation that returns aggregate information about an existing document without modifying, executing against external systems, or deleting data.
Documented attack patterns abuse exactly the kind of access lattice_stats gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Lattice, and nothing reaches the server without passing your rules. This is the rule we recommend for lattice_stats:
{
"version": "1",
"default": "deny",
"tools": {
"lattice_stats": {}
}
}lattice_stats 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 statistics about the currently loaded document. It is categorised as a Read tool in the Lattice MCP Server, which means it retrieves data without modifying state.
Register the Lattice MCP server in PolicyLayer and add a rule for lattice_stats: 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 Lattice. Nothing to install.
lattice_stats 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 lattice_stats 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 lattice_stats. 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.
lattice_stats is provided by the Lattice MCP server (yogthos/matryoshka). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 15 Lattice tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
15 Lattice tools catalogued and risk-classified — across an index of 42,500+ MCP servers.