Resolve a pending (llm_query …) suspension with a single string response. When lattice_query hits (llm_query …) and the client doesn
AI agents invoke lattice_llm_respond 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 resumes/continues a suspended engine computation by injecting a response, which constitutes triggering an external operation whose effects depend on the provided argument. It is not a simple read or write; it drives execution flow in the Lattice engine.
From the tool's definition 'Resolve a pending (llm_query …) suspension with a single string response' — triggers external operation by resuming a suspended computation in the Lattice engine
Documented attack patterns abuse exactly the kind of access lattice_llm_respond 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_llm_respond:
{
"version": "1",
"default": "deny",
"tools": {
"lattice_llm_respond": {
"limits": [
{
"counter": "lattice_llm_respond_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}lattice_llm_respond 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.
Resolve a pending (llm_query …) suspension with a single string response. When lattice_query hits (llm_query …) and the client doesn. 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_llm_respond: 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_llm_respond 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_llm_respond 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_llm_respond. 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_llm_respond 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.