Mixpanel Ingestion connector for AI agents

Tools your data agent reaches for on Mixpanel Ingestion, scoped per tenant.

CALL ANY TOOL

Event ingestion and profile management in one toolkit: import events, set and union profile properties, group profiles, identity merges, lookup tables, and flag evaluation.

mixpanelingestion_feature_flags_definitions

Feature flags definitions

Get the full definitions of every feature flag/experiment configured in a Mixpanel project, including each flag's variants, rollout rules, and linked experiment. Provide either 'project_token' or 'project_id' to authenticate (project_id uses your Service Account credentials).

Parameters

Name

Type

Required

Description

project_id

string

Optional

Your numeric Mixpanel Project ID, used if authenticating with a Service Account. Provide this or 'project_token'.

project_token

string

Optional

Your Mixpanel Project Token, used if authenticating without a Service Account. Provide this or 'project_id'.

mixpanelingestion_feature_flags_evaluate

Feature flags evaluate

mixpanelingestion_group_batch_update

Update group batch

mixpanelingestion_group_delete

Delete group

mixpanelingestion_group_remove

Remove group

mixpanelingestion_group_set

Set group

mixpanelingestion_group_set_once

Group set once

mixpanelingestion_group_union

Group union

mixpanelingestion_group_unset

Group unset

mixpanelingestion_identity_create

Create identity

mixpanelingestion_identity_create_alias

Identity create alias

mixpanelingestion_identity_merge

Merge identity

mixpanelingestion_import_events

Import events

mixpanelingestion_lookup_table_replace

Lookup table replace

mixpanelingestion_lookup_tables_list

List lookup tables

mixpanelingestion_profile_append

Profile append

mixpanelingestion_profile_batch_update

Update profile batch

mixpanelingestion_profile_delete

Delete profile

mixpanelingestion_profile_increment

Profile increment

mixpanelingestion_profile_remove

Remove profile

mixpanelingestion_profile_set

Set profile

mixpanelingestion_profile_set_once

Profile set once

mixpanelingestion_profile_union

Profile union

mixpanelingestion_profile_unset

Profile unset

mixpanelingestion_track_event

Track event

Build your Agent

Drop the toolkit in, point it at the tenant, and your agent can import events and update profiles 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: ["mixpanelingestion"], toolNames: ["mixpanelingestion_import_events", "mixpanelingestion_profile_set", "mixpanelingestion_identity_merge"] },
  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: ["mixpanelingestion"], toolNames: ["mixpanelingestion_import_events", "mixpanelingestion_profile_set", "mixpanelingestion_identity_merge"] },
  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: ["mixpanelingestion"], toolNames: ["mixpanelingestion_import_events", "mixpanelingestion_profile_set", "mixpanelingestion_identity_merge"] },
  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/mixpanelingestion",
    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 running Mixpanel ingestion from your workflows.

Event import

Copy the prompt

Copied

Import these events for [date] and report anything rejected.

Copy the prompt

Copied

Backfill signup events for last week and dedupe on insert_id.

Copy the prompt

Copied

Track a single [event] for distinct_id [id] with these properties.

Profiles and groups

Copy the prompt

Copied

Set plan and mrr on profile [distinct_id].

Copy the prompt

Copied

Union the feature_flags property on these profiles instead of overwriting.

Copy the prompt

Copied

Batch update group profiles for org [group_id].

Identity and lookups

Copy the prompt

Copied

Merge distinct_id [a] into [b] and confirm the surviving id.

Copy the prompt

Copied

Replace the lookup table for plan tiers with this CSV.

Copy the prompt

Copied

Evaluate feature flags for distinct_id [id].

SEE HOW AUTH WORKS

You connect a service account once. Your Mixpanel Ingestion credentials stay vaulted, every call is scope-checked, and every action is logged.

Authorize

Your user connects

Mixpanel Ingestion

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

Store

Their

Mixpanel Ingestion

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

Resolve

When your agent calls a

Mixpanel Ingestion

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

Audit

Every

Mixpanel Ingestion

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 auth, scope, and audit pattern across other connectors.

GTM and RevOps Teams

Revenue forecast commentary

Pulls open pipeline from Salesforce and HubSpot, calculates coverage against quota, flags at-risk stages, posts commentary to Slack, and logs every snapshot to Google Sheets.

GTM and RevOps Teams

Deal intelligence agent

Pulls recent Gong calls, scores deal risk with an LLM, cross-references the record in Attio, and DMs each owner their at-risk deals in Slack. Every read is scoped to that rep's own access.

Engineering Teams

Engineering standup agent

Pulls commits from GitHub and GitLab, tracks issue movement in Jira, and posts a per-engineer standup brief to Slack. Each engineer's activity is read on their own delegated OAuth.

GTM and RevOps Teams

Competitive intelligence briefing agent

Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production you need to know which agent and tenant made each call. Scalekit resolves the tenant's vaulted service account 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 Ingestion 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

How does the agent authenticate to Mixpanel Ingestion?

You connect Mixpanel Ingestion once with a service account, and Scalekit authenticates every call. Audit logs record every action the agent takes.

Where are the Mixpanel Ingestion service account credentials stored?

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

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

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 Ingestion.

What happens when the Mixpanel Ingestion service account is revoked?

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

What stops an agent from writing junk events into production?

Scope and separation. Ingestion tools are separate from the delete and lookup-replace tools, so you expose only what a given agent needs. Every call is scope-checked before it reaches Mixpanel, attributed to the calling agent and tenant, and kept in the 90-day audit chain for replay.