Make a GET request to any Upmind API endpoint
AI agents call api_get to retrieve information from Upmind 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 data from the Upmind API without modifying, deleting, or executing arbitrary operations. GET requests are inherently read-only operations that query existing data. While the tool's generality (any endpoint) introduces some risk if an agent makes requests to sensitive data endpoints, the fundamental operation is retrieval only, making it a Read category tool.
From the tool's definition Tool name is 'api_get' and description states 'Make a GET request to any Upmind API endpoint'. GET requests are the standard HTTP method for retrieving data without side effects.
Attacks that exploit this kind of access
Make a GET request to any Upmind API endpoint. It is categorised as a Read tool in the Upmind MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Upmind MCP Server MCP server in PolicyLayer and add a rule for api_get: 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 Upmind MCP Server. Nothing to install.
api_get 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 api_get 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 api_get. 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.
api_get is provided by the Upmind MCP Server MCP server (stardeltapower/upmind-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 →