Expert mode legal analysis — runs the full verification pipeline for a more detailed, deeply-cited answer. Slower than ask.
Risk signalsAccepts freeform code/query input (query)
Part of the 법마디(Lawmadi) OS — Korean Legal AI server.
Free to start. No card required.
AI agents call ask_expert to retrieve information from 법마디(Lawmadi) OS — Korean Legal AI without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though ask_expert only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"ask_expert": {}
}
}See the full 법마디(Lawmadi) OS — Korean Legal AI policy for all 6 tools.
These attack patterns abuse exactly the kind of access ask_expert gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Expert mode legal analysis — runs the full verification pipeline for a more detailed, deeply-cited answer. Slower than ask.. It is categorised as a Read tool in the 법마디(Lawmadi) OS — Korean Legal AI MCP Server, which means it retrieves data without modifying state.
Register the 법마디(Lawmadi) OS — Korean Legal AI MCP server in PolicyLayer and add a rule for ask_expert: 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 법마디(Lawmadi) OS — Korean Legal AI. Nothing to install.
ask_expert 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 ask_expert 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 ask_expert. 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.
ask_expert is provided by the 법마디(Lawmadi) OS — Korean Legal AI MCP server (https://lawmadi.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 법마디(Lawmadi) OS — Korean Legal AI tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.