Compatible with every major AI agent and IDE
What is the Umami (Privacy Analytics) MCP Server?
Connect your Umami instance to any AI agent to monitor your privacy-focused analytics and manage your infrastructure through natural language. Umami is the open-source, privacy-friendly alternative to Google Analytics, and this MCP server gives you full control over your data.
What you can do
- Event Tracking — Send custom events and page views directly to your Umami instance using the
send_eventtool. - Website Management — List and manage all websites associated with your account or the entire instance using
get_me_websitesoradmin_list_websites. - User & Team Administration — Perform administrative tasks like creating, updating, or deleting users and managing teams with tools like
create_userandadmin_list_teams. - Session Insights — Retrieve information about your current session and authorized access levels using
get_me. - Self-Hosted Support — Seamlessly connect to your own infrastructure using the
logintool to authenticate and retrieve tokens.
How it works
- Subscribe to this server
- Provide your Umami Instance URL and API Key (or use the login tool)
- Start querying your analytics data or managing users from Claude, Cursor, or any MCP client
Who is this for?
- Data Analysts — quickly pull website lists and verify tracking status without leaving the chat interface.
- DevOps & Admins — automate user provisioning and team management on self-hosted Umami instances.
- Growth Marketers — trigger test events and verify analytics pipelines during development.
Built-in capabilities (53)
Add user to team
Returns all teams (Admin only)
Returns all users (Admin only)
Returns all websites (Admin only)
Marketing attribution report
Conversion funnel report
Creates a link
Creates a pixel
Creates a report
User retention report
Revenue report
Creates a team
Creates a user (Admin only)
Creates a website
Deletes a user (Admin only)
Deletes a website
Get information about the current session
Get all teams for the current user
Get all websites for the current user
Realtime stats within the last 30 minutes
Individual session details
Activity for a session
Get team members
Get team websites
Gets a user by ID (Admin only)
Gets all teams belonging to a user (Admin only)
Gets all websites belonging to a user (Admin only)
Gets a website by ID
Active users in the last 5 minutes
Available data date range
Event data grouped by event
Event data names and counts
Property and value counts
Website event details
Aggregated event statistics
Metrics for a given time range (type: path, browser, os, etc.)
Expanded metrics including bounces and total time
Pageviews and sessions series data
Website session details
Summarized session statistics
Summarized website statistics (pageviews, visitors, etc.)
Join a team via access code
Returns all user links
Returns all user pixels
Get all reports by website ID
Returns all teams
Returns all user websites
Login to self-hosted Umami to get a token
Removes all data related to the website
Send an event to Umami
Updates a user (Admin only)
Updates a website
Verify if the current token is still valid
Why Pydantic AI?
Pydantic AI validates every Umami (Privacy Analytics) tool response against typed schemas, catching data inconsistencies at build time. Connect 53 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Umami (Privacy Analytics) integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Umami (Privacy Analytics) connection logic from agent behavior for testable, maintainable code
Umami (Privacy Analytics) in Pydantic AI
Umami (Privacy Analytics) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Umami (Privacy Analytics) to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Umami (Privacy Analytics) in Pydantic AI
The Umami (Privacy Analytics) MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 53 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Umami (Privacy Analytics) for Pydantic AI
Every tool call from Pydantic AI to the Umami (Privacy Analytics) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I use this with my self-hosted Umami instance?
Yes. You can provide your custom instance URL and use the login tool to authenticate, or provide a pre-generated API key/token.
How do I track a custom event from the AI?
Use the send_event tool. You'll need to provide the website ID and the url. You can also include optional metadata like name and data objects.
Can I manage other users if I am an admin?
Absolutely. If your credentials have admin rights, you can use admin_list_users, create_user, update_user, and delete_user to manage the instance population.
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your Umami (Privacy Analytics) MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai
Explore More MCP Servers
View all →
Equixly
10 toolsAutomate API security testing via Equixly — manage target services, trigger autonomous AI pentests, and audit vulnerability findings directly from any AI agent.

EBI InterPro
16 toolsClassify protein sequences into families, predict functional domains, and explore evolutionary relationships across species.

Ziflow
12 toolsEnterprise online proofing and content review platform to manage creative workflows with AI.

Epic Online Services & Social Analytics
8 toolsThe definitive server for Epic Games social intelligence — track player profiles, friends, and achievements via AI.
