Transform data using LLM with custom instructions and JSON schema validation
AI agents invoke llm.transform to trigger actions in LCBro. 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 an LLM inference call with arbitrary user-provided instructions and applies JSON schema validation to the output. The 'custom instructions' aspect means it can trigger arbitrary LLM processing with unpredictable side effects depending on the instructions passed. It spans Execute territory as it runs an external LLM operation rather than simply reading or writing structured data.
From the tool's definition Transform data using LLM with custom instructions and JSON schema validation
Documented attack patterns abuse exactly the kind of access llm.transform gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and LCBro, and nothing reaches the server without passing your rules. This is the rule we recommend for llm.transform:
{
"version": "1",
"default": "deny",
"tools": {
"llm.transform": {
"limits": [
{
"counter": "llm.transform_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}llm.transform 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.
Transform data using LLM with custom instructions and JSON schema validation. It is categorised as a Execute tool in the LCBro MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the LCBro MCP server in PolicyLayer and add a rule for llm.transform: 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 LCBro. Nothing to install.
llm.transform 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 llm.transform 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 llm.transform. 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.
llm.transform is provided by the LCBro MCP server (lcbro/lcbro-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from LCBro, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
11 LCBro tools catalogued and risk-classified — across an index of 43,000+ MCP servers.