AI agents invoke lattice_query to trigger actions in Lattice. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool executes a Nucleus DSL query against a document, which constitutes running code/commands whose effects depend on the query arguments. While it appears to primarily read/retrieve data from the document, the use of 'Execute' in the description and the DSL execution model mean arbitrary Nucleus commands could have broader side effects.
From the tool's definition "Execute a Nucleus query on the loaded document" — the tool explicitly runs/executes a query using the Nucleus DSL on a loaded document.
Documented attack patterns abuse exactly the kind of access lattice_query 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_query:
{
"version": "1",
"default": "deny",
"tools": {
"lattice_query": {
"limits": [
{
"counter": "lattice_query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}lattice_query stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute a Nucleus query on the loaded document. It is categorised as a Execute tool in the Lattice MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Lattice MCP server in PolicyLayer and add a rule for lattice_query: 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_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the lattice_query 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_query. 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_query 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.