Multi-turn chat with MiniMax AI. Supports conversation context preservation across multiple calls.
AI agents invoke minimax_chat to trigger actions in My Minimax. 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.
The tool sends messages to an external AI service (MiniMax), triggering external operations with effects dependent on the conversation content. Given the server's purpose as an autonomous code executor, chat interactions may trigger code generation and execution.
From the tool's definition 'Multi-turn chat with MiniMax AI' and server description states it wraps MiniMax AI 'as an autonomous code executor' that can execute coding tasks
Attacks that exploit this kind of access
Multi-turn chat with MiniMax AI. Supports conversation context preservation across multiple calls. It is categorised as a Execute tool in the My Minimax MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the My Minimax MCP server in PolicyLayer and add a rule for minimax_chat: 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 My Minimax. Nothing to install.
minimax_chat 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 minimax_chat 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 minimax_chat. 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.
minimax_chat is provided by the My Minimax MCP server (wongo/my-minimax-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →