Run custom JQL (JSON Query Language) queries. Useful for advanced analytics and custom data analysis beyond standard reports.
AI agents invoke custom_jql to trigger actions in Mixpanel MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool allows execution of arbitrary query language commands (JQL) whose effects depend entirely on the arguments provided by the user or AI agent. While the queries appear to be read-only analytics operations (based on the sibling tools being queries and reports), the ability to run 'custom' and 'advanced' queries means the tool can potentially access any data the Mixpanel account exposes, create derived data,…
From the tool's definition Tool name 'custom_jql' and description explicitly states 'Run custom JQL (JSON Query Language) queries', indicating execution of user-supplied query language code against the Mixpanel analytics backend.
Attacks that exploit this kind of access
Run custom JQL (JSON Query Language) queries. Useful for advanced analytics and custom data analysis beyond standard reports. It is categorised as a Execute tool in the Mixpanel MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mixpanel MCP server in PolicyLayer and add a rule for custom_jql: 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. Nothing to install.
custom_jql is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the custom_jql 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 custom_jql. 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.
custom_jql is provided by the Mixpanel MCP server (mendeel/mixpanel-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 →