get_cgm_sandbox
AI agents call get_cgm_sandbox to retrieve information from T1D Manager without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve CGM data, which is a read operation with no data modification. However, confidence is moderate (0.75) rather than high because the description is empty, preventing full certainty about its exact behavior.
From the tool's definition Tool name 'get_cgm_sandbox' suggests retrieval of continuous glucose monitor (CGM) data from a sandbox/test environment. The 'get_' prefix and sibling tools like 'get_cgm_data' and 'get_cgm_with_token' consistently indicate read operations.
Attacks that exploit this kind of access
get_cgm_sandbox. It is categorised as a Read tool in the T1D Manager MCP Server, which means it retrieves data without modifying state.
Register the T1D Manager MCP server in PolicyLayer and add a rule for get_cgm_sandbox: 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 T1D Manager. Nothing to install.
get_cgm_sandbox 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_cgm_sandbox 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_cgm_sandbox. 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_cgm_sandbox is provided by the T1D Manager MCP server (junhyungkang/t1d-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 →