Umami (Privacy Analytics) MCP Server for Pydantic AIGive Pydantic AI instant access to 53 tools to Add Team User, Admin List Teams, Admin List Users, and more
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Umami (Privacy Analytics) through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.
Ask AI about this MCP Server for Pydantic AI
The Umami (Privacy Analytics) MCP Server for Pydantic AI is a standout in the Marketing Automation category — giving your AI agent 53 tools to work with, ready to go from day one.
Vinkius delivers Streamable HTTP and SSE to any MCP client
import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
agent = Agent(
model="openai:gpt-4o",
mcp_servers=[server],
system_prompt=(
"You are an assistant with access to Umami (Privacy Analytics) "
"(53 tools)."
),
)
result = await agent.run(
"What tools are available in Umami (Privacy Analytics)?"
)
print(result.data)
asyncio.run(main())
* 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
About 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.
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.
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.
The Umami (Privacy Analytics) MCP Server exposes 53 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — credentials fully managed, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
All 53 Umami (Privacy Analytics) tools available for Pydantic AI
When Pydantic AI connects to Umami (Privacy Analytics) through Vinkius, your AI agent gets direct access to every tool listed below — spanning web-analytics, privacy-focused, event-tracking, and more. Every call runs in a secure, isolated environment with full audit visibility. Beyond a simple connection, you get real-time monitoring of agent activity, enterprise governance, and optimized token usage.
Add team user on Umami (Privacy Analytics)
Add user to team
Admin list teams on Umami (Privacy Analytics)
Returns all teams (Admin only)
Admin list users on Umami (Privacy Analytics)
Returns all users (Admin only)
Admin list websites on Umami (Privacy Analytics)
Returns all websites (Admin only)
Create attribution report on Umami (Privacy Analytics)
Marketing attribution report
Create funnel report on Umami (Privacy Analytics)
Conversion funnel report
Create link on Umami (Privacy Analytics)
Creates a link
Create pixel on Umami (Privacy Analytics)
Creates a pixel
Create report on Umami (Privacy Analytics)
Creates a report
Create retention report on Umami (Privacy Analytics)
User retention report
Create revenue report on Umami (Privacy Analytics)
Revenue report
Create team on Umami (Privacy Analytics)
Creates a team
Create user on Umami (Privacy Analytics)
Creates a user (Admin only)
Create website on Umami (Privacy Analytics)
Creates a website
Delete user on Umami (Privacy Analytics)
Deletes a user (Admin only)
Delete website on Umami (Privacy Analytics)
Deletes a website
Get me on Umami (Privacy Analytics)
Get information about the current session
Get me teams on Umami (Privacy Analytics)
Get all teams for the current user
Get me websites on Umami (Privacy Analytics)
Get all websites for the current user
Get realtime stats on Umami (Privacy Analytics)
Realtime stats within the last 30 minutes
Get session on Umami (Privacy Analytics)
Individual session details
Get session activity on Umami (Privacy Analytics)
Activity for a session
Get team users on Umami (Privacy Analytics)
Get team members
Get team websites on Umami (Privacy Analytics)
Get team websites
Get user on Umami (Privacy Analytics)
Gets a user by ID (Admin only)
Get user teams on Umami (Privacy Analytics)
Gets all teams belonging to a user (Admin only)
Get user websites on Umami (Privacy Analytics)
Gets all websites belonging to a user (Admin only)
Get website on Umami (Privacy Analytics)
Gets a website by ID
Get website active on Umami (Privacy Analytics)
Active users in the last 5 minutes
Get website daterange on Umami (Privacy Analytics)
Available data date range
Get website event data on Umami (Privacy Analytics)
Event data grouped by event
Get website event data events on Umami (Privacy Analytics)
Event data names and counts
Get website event data fields on Umami (Privacy Analytics)
Property and value counts
Get website events on Umami (Privacy Analytics)
Website event details
Get website events stats on Umami (Privacy Analytics)
Aggregated event statistics
Get website metrics on Umami (Privacy Analytics)
Metrics for a given time range (type: path, browser, os, etc.)
Get website metrics expanded on Umami (Privacy Analytics)
Expanded metrics including bounces and total time
Get website pageviews on Umami (Privacy Analytics)
Pageviews and sessions series data
Get website sessions on Umami (Privacy Analytics)
Website session details
Get website sessions stats on Umami (Privacy Analytics)
Summarized session statistics
Get website stats on Umami (Privacy Analytics)
Summarized website statistics (pageviews, visitors, etc.)
Join team on Umami (Privacy Analytics)
Join a team via access code
List links on Umami (Privacy Analytics)
Returns all user links
List pixels on Umami (Privacy Analytics)
Returns all user pixels
List reports on Umami (Privacy Analytics)
Get all reports by website ID
List teams on Umami (Privacy Analytics)
Returns all teams
List websites on Umami (Privacy Analytics)
Returns all user websites
Login on Umami (Privacy Analytics)
Login to self-hosted Umami to get a token
Reset website on Umami (Privacy Analytics)
Removes all data related to the website
Send event on Umami (Privacy Analytics)
Send an event to Umami
Update user on Umami (Privacy Analytics)
Updates a user (Admin only)
Update website on Umami (Privacy Analytics)
Updates a website
Verify token on Umami (Privacy Analytics)
Verify if the current token is still valid
Connect Umami (Privacy Analytics) to Pydantic AI via MCP
Follow these steps to wire Umami (Privacy Analytics) into Pydantic AI. The entire setup takes under two minutes — your credentials stay safe behind Vinkius.
Install Pydantic AI
pip install pydantic-aiReplace the token
[YOUR_TOKEN_HERE] with your Vinkius tokenRun the agent
agent.py and run: python agent.pyExplore tools
Why Use Pydantic AI with the Umami (Privacy Analytics) MCP Server
Pydantic AI provides unique advantages when paired with Umami (Privacy Analytics) through the Model Context Protocol.
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) + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the Umami (Privacy Analytics) MCP Server delivers measurable value.
Type-safe data pipelines: query Umami (Privacy Analytics) with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple Umami (Privacy Analytics) tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query Umami (Privacy Analytics) and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock Umami (Privacy Analytics) responses and write comprehensive agent tests
Example Prompts for Umami (Privacy Analytics) in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with Umami (Privacy Analytics) immediately.
"List all websites I have access to in Umami."
"Send a 'newsletter_signup' event for website 8f2...1a on page /thanks."
"Show me all users on this Umami instance."
Troubleshooting Umami (Privacy Analytics) MCP Server with Pydantic AI
Common issues when connecting Umami (Privacy Analytics) to Pydantic AI through Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiUmami (Privacy Analytics) + Pydantic AI FAQ
Common questions about integrating Umami (Privacy Analytics) MCP Server with Pydantic AI.
How does Pydantic AI discover MCP tools?
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?
Can I switch LLM providers without changing MCP code?
Explore More MCP Servers
View all →
IndoorAtlas (Indoor Positioning)
10 toolsManage indoor positioning via IndoorAtlas — list venues, upload floorplans, and analyze positioning sessions.

Google Cloud Storage
12 toolsManage your GCS buckets and objects — list files, upload data, and audit permissions via AI.

Integrate.io (ETL & Data Integration)
6 toolsManage data pipelines via Integrate.io — list pipelines, monitor job runs, and audit data transformations.

Mux
11 toolsManage video assets and live streams via Mux — create assets and track performance directly from your AI agent.
