get-model-topic-tree
AI agents call get-model-topic-tree to retrieve information from supos MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries a topic tree structure from supOS with no apparent side effects. The 'get-' prefix and context of query-based tools indicate read-only access. The empty description lowers confidence slightly, but the consistent pattern across sibling tools and server purpose strongly suggests this is a read operation. No destructive, write, execute, or financial operations are indicated.
From the tool's definition Tool name 'get-model-topic-tree' and sibling tools 'get-topic-realtime-data', 'get-model-topic-detail', 'get-all-topic-realtime-data' all use 'get-' prefix indicating retrieval operations.
Attacks that exploit this kind of access
get-model-topic-tree. It is categorised as a Read tool in the supos MCP Server MCP Server, which means it retrieves data without modifying state.
Register the supos MCP Server MCP server in PolicyLayer and add a rule for get-model-topic-tree: 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 supos MCP Server. Nothing to install.
get-model-topic-tree 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 get-model-topic-tree 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 get-model-topic-tree. 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.
get-model-topic-tree is provided by the supos MCP Server MCP server (zantiu/mcp-server-supos). 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 →