Get a user
AI agents call user_activity to retrieve information from Mixpanel 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 user activity/profile data from Mixpanel without modifying, deleting, or executing external operations. It fits the 'Read' category as a straightforward data query operation. Severity is low because accessing user analytics data has minimal blast radius—it cannot delete data, execute code, or cause financial impact.
From the tool's definition Tool name 'user_activity' with description 'Get a user' clearly indicates a retrieval operation. The MCP server description confirms it provides 'access to the Mixpanel REST API, enabling AI agents to query events, funnels, retention data, and user profiles.'…
Attacks that exploit this kind of access
Get a user. It is categorised as a Read tool in the Mixpanel MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Mixpanel MCP Server MCP server in PolicyLayer and add a rule for user_activity: 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 Mixpanel MCP Server. Nothing to install.
user_activity 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 user_activity 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 user_activity. 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.
user_activity is provided by the Mixpanel MCP Server MCP server (t-campbell18/mcp-mixpanel). 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 →