AI agents invoke consult_aurai to trigger actions in Aurai Advisor (上级顾问 MCP). 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.
Based on the server description, this tool likely triggers an external API call to a remote AI provider, which constitutes executing an external operation. The sibling tools (get_status, report_progress, sync_context) suggest a workflow where consult_aurai initiates a consultation session.
From the tool's definition Tool name 'consult_aurai' on a server described as enabling local AI models to receive guidance from remote 'senior' AI providers (OpenAI, Anthropic, Gemini). Description is empty.
Documented attack patterns abuse exactly the kind of access consult_aurai gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Aurai Advisor (上级顾问 MCP), and nothing reaches the server without passing your rules. This is the rule we recommend for consult_aurai:
{
"version": "1",
"default": "deny",
"tools": {
"consult_aurai": {
"limits": [
{
"counter": "consult_aurai_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}consult_aurai 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.
consult_aurai. It is categorised as a Execute tool in the Aurai Advisor (上级顾问 MCP) MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Aurai Advisor (上级顾问 MCP) MCP server in PolicyLayer and add a rule for consult_aurai: 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 Aurai Advisor (上级顾问 MCP). Nothing to install.
consult_aurai 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 consult_aurai 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 consult_aurai. 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.
consult_aurai is provided by the Aurai Advisor (上级顾问 MCP) MCP server (lzmw/mcp-aurai-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Aurai Advisor (上级顾问 MCP), 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.
4 Aurai Advisor (上级顾问 MCP) tools catalogued and risk-classified — across an index of 43,000+ MCP servers.