amplitude_get_new_users
AI agents call amplitude_get_new_users to retrieve information from Integrations MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get' verb and context from sibling Amplitude tools indicate this retrieves analytics metrics without modification. While the empty description lowers confidence slightly, the tool name and pattern of related read-only analytics tools establish this as a Read operation with minimal risk—it only queries existing data from an analytics platform.
From the tool's definition Tool name 'amplitude_get_new_users' indicates a retrieval operation ('get') on Amplitude analytics data. Sibling tools like 'amplitude_get_active_users' and 'amplitude_get_event_counts' are clearly read-only analytics queries.
Attacks that exploit this kind of access
amplitude_get_new_users. It is categorised as a Read tool in the Integrations MCP MCP Server, which means it retrieves data without modifying state.
Register the Integrations MCP server in PolicyLayer and add a rule for amplitude_get_new_users: 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 Integrations MCP. Nothing to install.
amplitude_get_new_users 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 amplitude_get_new_users 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 amplitude_get_new_users. 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.
amplitude_get_new_users is provided by the Integrations MCP server (shriram-vasudevan/integrations-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 →