
Mixpanel MCP Connector
Enables ChatGPT to query and analyze Mixpanel analytics data in real-time. Provides live access to event segmentation and detailed analytics data from your Mixpanel project through natural language.
README
Mixpanel → ChatGPT MCP Connector (Cloud Run)
This is a no-frills bridge that lets ChatGPT query your Mixpanel project live.
What it exposes
POST /tools/search
— summarize a segmentation queryPOST /tools/fetch
— return the full Mixpanel JSON for a prior searchGET /healthz
— health check
Environment variables
MIXPANEL_BASE
—https://mixpanel.com/api
orhttps://eu.mixpanel.com/api
orhttps://in.mixpanel.com/api
MIXPANEL_PROJECT_ID
— your Mixpanel project id (number)MIXPANEL_SA_USERNAME
— service account usernameMIXPANEL_SA_SECRET
— service account secretALLOWED_EVENTS
— optional CSV whitelist (recommended)
Local run (optional)
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
export $(cat sample.env | xargs) && uvicorn app:app --host 0.0.0.0 --port 8080
Cloud Run (one-time)
gcloud services enable run.googleapis.com cloudbuild.googleapis.com artifactregistry.googleapis.com
REGION=us-central1
REPO=mcp-bridge
IMAGE=${REGION}-docker.pkg.dev/$(gcloud config get-value project)/$REPO/mixpanel-mcp:1
gcloud artifacts repositories create $REPO --repository-format=docker --location=$REGION --description="MCP images" || true
gcloud builds submit --tag $IMAGE .
gcloud run deploy mixpanel-mcp --image $IMAGE --region $REGION --platform managed --allow-unauthenticated --min-instances=0 --set-env-vars MIXPANEL_BASE=https://mixpanel.com/api --set-env-vars MIXPANEL_PROJECT_ID=YOUR_PROJECT_ID --set-env-vars MIXPANEL_SA_USERNAME=YOUR_SERVICE_ACCOUNT_USERNAME --set-env-vars MIXPANEL_SA_SECRET=YOUR_SERVICE_ACCOUNT_SECRET --set-env-vars ALLOWED_EVENTS=sign_up_success,listing_viewed,job_matcher_attempt,search_initiated
After deploy, note the service URL:
https://mixpanel-mcp-xxxxx-uc.a.run.app
Testing
- Health:
GET /healthz
- Search:
POST /tools/search
{"event":"sign_up_success","from_date":"2025-08-24","to_date":"2025-08-31","unit":"day","breakdown":"properties[\"platform\"]"}
- Fetch the returned
id
:
POST /tools/fetch
{"objectIds":["<id from search>"]}
Add to ChatGPT
Settings → Connectors → Add → Custom Connector (MCP) → paste your Cloud Run URL.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.