Mixpanel Compliance connector for AI agents

CALL ANY TOOL

GDPR requests end to end: create and cancel deletion tasks, file subject access retrievals, and poll status on both. The bearer token stays vaulted per tenant.

mixpanelcompliance_gdpr_deletion_create

Create gdpr deletion

Permanently delete all data mixpanel holds for the given distinct_ids: every event and profile property, across all time. this is irreversible once processing completes, and per mixpanel's gdpr/ccpa documentation it can take up to 30 days to fully propagate through mixpanel's systems. only call this to fulfill a genuine right-to-erasure request: never speculatively or for testing. use 'mixpanelcompliance_gdpr_deletion_status' with the returned tracking_id to monitor progress, and 'mixpanelcompliance_gdpr_deletion_cancel' to attempt to stop it before processing starts.

Parameters

Name

Type

Required

Description

distinct_ids

array

Required

The Mixpanel distinct_ids whose data will be PERMANENTLY deleted. This cannot be undone. Mixpanel accepts at most 1999 distinct_ids per deletion request: split larger batches into multiple calls.

project_token

string

Required

Your Mixpanel Project Token (Project Settings > Overview), identifying which project to run this request against. Sent as the 'token' query parameter. This is distinct from the GDPR Compliance Token used to authenticate this connection.

compliance_type

string

Optional

The privacy regulation this request is being made under. Defaults to 'GDPR' when omitted.

mixpanelcompliance_gdpr_retrieval_create

Create gdpr retrieval

mixpanelcompliance_gdpr_deletion_cancel

Cancel gdpr deletion

mixpanelcompliance_gdpr_deletion_status

Gdpr deletion status

mixpanelcompliance_gdpr_retrieval_status

Gdpr retrieval status

Build your Agent

Drop the toolkit in, point it at the tenant, and your agent can file and track erasure requests from the first run.

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["mixpanelcompliance"], toolNames: ["mixpanelcompliance_gdpr_deletion_create", "mixpanelcompliance_gdpr_deletion_status", "mixpanelcompliance_gdpr_retrieval_create"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["mixpanelcompliance"], toolNames: ["mixpanelcompliance_gdpr_deletion_create", "mixpanelcompliance_gdpr_deletion_status", "mixpanelcompliance_gdpr_retrieval_create"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["mixpanelcompliance"], toolNames: ["mixpanelcompliance_gdpr_deletion_create", "mixpanelcompliance_gdpr_deletion_status", "mixpanelcompliance_gdpr_retrieval_create"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/mixpanelcompliance",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start filing Mixpanel GDPR requests from your workflows.

Right to erasure

Copy the prompt

Copied

File a deletion request for distinct_ids [a] and [b].

Copy the prompt

Copied

Check the status of deletion task [task_id].

Copy the prompt

Copied

Cancel deletion task [task_id] before it starts erasing.

Subject access

Copy the prompt

Copied

Create a subject access request for distinct_id [id].

Copy the prompt

Copied

Poll retrieval task [task_id] and tell me when the export is ready.

Copy the prompt

Copied

Summarize which data sources a retrieval covers.

Audit trail

Copy the prompt

Copied

List every deletion request filed this quarter and its outcome.

Copy the prompt

Copied

Who filed the erasure request for [distinct_id]?

Copy the prompt

Copied

Show requests still pending after 7 days.

SEE HOW AUTH WORKS

Your users connect once. Their Mixpanel Compliance credentials stay vaulted, every call is scope-checked, and every action is logged.

1

Authorize

Your user connects

Mixpanel Compliance

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

Mixpanel Compliance

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

Mixpanel Compliance

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

Mixpanel Compliance

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other connectors.

SALES

Deal intelligence agent

Score Gong call risk with an LLM, cross-reference the Attio record, and DM each owner their at-risk deals in Slack.

ENGINEERING

Engineering standup agent

Pull commits from GitHub and GitLab, track Jira issue movement, and post a per-engineer standup brief to Slack.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
audit → bot_service_account
user_filter → broken

// scalekit
audit → user_abc
scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Mixpanel Compliance today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Mixpanel Compliance as the user or as a shared key?

As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Mixpanel Compliance bearer token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Mixpanel Compliance?

Yes. Pass a tool name filter to listScopedTools so the analytics agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Mixpanel Compliance.

What happens when a user revokes Mixpanel Compliance access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Who is on record as filing a GDPR deletion?

The authorizing user, not a service account. Scalekit resolves that user's credential at request time and writes the action into the 90-day audit chain with the tool name, tenant, and timestamp, which is the evidence trail a data protection review needs.

Mixpanel Compliance

Tools your compliance agent reaches for on Mixpanel Compliance, scoped per tenant.