Pendo MCP Server | Connect Product Analytics to Any AI Tool
PENDO MCP SERVER
Turn any AI tool into a product expert with Pendo’s MCP server.
Connect Pendo with your AI workflows to get instant access to usage data, visitor behavior, and customer context, wherever you work.
Learn how to set up Pendo MCP in this 1-minute demo.
The state of the agent
Todd Olson (Pendo) and Dave Meyer (Atlassian) on what's working with AI agents in 2026 — plus real-world stories from Teachable and Pendo's own product team.
Put product insights into everyone's hands.
Not everyone uses Pendo, but everyone needs its data. With MCP, anyone from sales reps to your CEO can get rich behavioral insights with just a few prompts.
AI that gets your business
Combine Pendo analytics with your CRM, support tickets, and more to make smarter decisions.
Answer questions, instantly
No more waiting, manually building reports, or submitting requests.
Break down data siloes
Give every team access to valuable insights, no Pendo knowledge required.
Pendo plugs into your favorite AI systems.
Connect Pendo to Claude instantly
How it works.
STEP 1
Connect Pendo to your AI agent of choice.
Pendo MCP makes product usage data accessible to AI agents through the Model Context Protocol (MCP), an open-source standard for securely connecting AI applications to external systems.
STEP 2
Ask your agent anything.
Type in a question, and watch as your AI system surfaces behavioral insights to answer your questions.
Pendo MCP can pull:
- Visitor and account metadata
- Application analytics and user behavior
- Page, feature, and track event data
- Event-level aggregation queries
- Visitor activity and engagement patterns
Security teams love Pendo.
Pendo adheres to key industry best practices and regulatory schemes to protect the security and privacy of our customers’ data: SOC 2, GDPR, HIPAA, and Privacy Shield.
Want to see Pendo’s MCP server for yourself?
Talk to an expert ->
Learn more about MCP.
What is the Pendo MCP server?
The Pendo Model Context Protocol (MCP) server is a standardized connection that lets you query your Pendo product analytics data through AI tools like Claude, ChatGPT, and Cursor using natural language. Instead of building reports or dashboards, you can ask questions like "which features have the highest adoption?" or "show me user behavior for enterprise accounts" and get instant answers directly in your AI workflow.
What is MCP and why does it matter?
Model Context Protocol (MCP) is an open standard that enables AI applications to securely connect to external data sources and tools. Introduced by Anthropic in November 2024, MCP works like USB-C for AI—it provides a universal way for AI platforms to access business data without building custom integrations for each tool.
For Pendo customers, this means your product analytics data becomes accessible wherever you work, from Claude Code to ChatGPT to Cursor.
Who can use the Pendo MCP server?
Any paid Pendo customer can access MCP. An admin must enable MCP for an organization to start using it.
What AI platforms does it work with?
Any AI platform or client that supports the Model Context Protocol, including Claude (web and desktop), Claude Code, Cursor, VS Code with GitHub Copilot, ChatGPT (developer mode), and more. As MCP becomes more widely adopted, even more platforms will be compatible.
What are the main use cases?
Common use cases include:
- Preparing for customer calls with real product context
- Investigating adoption or churn signals
- Enriching support tickets with usage data
- Building AI agents or assistants powered by product data
- Ad-hoc analysis without building reports
- Analyzing feature usage and engagement patterns
Is this secure? What data does AI see?
The MCP server uses OAuth authentication and respects existing Pendo permissions, users can only access data they're already authorized to view in Pendo. Important note: The AI service (e.g., Anthropic, OpenAI) processes your Pendo data to answer queries, so organizations should review their AI data policies and compliance requirements (GDPR, CCPA, etc.) before implementation.