Execute Nucleus commands directly on a document without LLM orchestration.
AI agents invoke nucleus_execute 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.
This tool executes arbitrary commands in the Nucleus DSL language on documents. While the effects are scoped to document processing rather than system-level operations, execution of user-supplied DSL commands without intermediary LLM validation represents a significant risk if an attacker can control the command input. The tool could be used to extract, transform, or manipulate document data in unintended ways.
From the tool's definition Tool name is 'nucleus_execute' and description states 'Execute Nucleus commands directly on a document without LLM orchestration.' The verb 'Execute' combined with the DSL execution capability indicates this runs code-like operations (Nucleus commands) whose…
Documented attack patterns abuse exactly the kind of access nucleus_execute 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 nucleus_execute:
{
"version": "1",
"default": "deny",
"tools": {
"nucleus_execute": {
"limits": [
{
"counter": "nucleus_execute_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}nucleus_execute 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 Nucleus commands directly on a document without LLM orchestration. 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 nucleus_execute: 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.
nucleus_execute 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 nucleus_execute 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 nucleus_execute. 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.
nucleus_execute 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.