Connect the Pendo MCP server to Unblocked to give AI agents live product usage context

Pendo knows which Pages and Features people actually use, which guides they see, and what happened in a visitor’s session — but none of that reaches the developer about to change or remove the feature. Pendo’s MCP server exposes usage, guides, and visitor activity to AI agents, and Unblocked connects to it once so every agent can ask how a feature is used without its own Pendo setup.

This is a third-party MCP server: Pendo hosts and maintains it, and Unblocked connects to it as a verified MCP server. Nothing is ingested or indexed — Unblocked calls the read-only tools you select at the moment a question needs them, so answers reflect your Pendo subscription’s usage data and guides as they are now.

Wiring Pendo’s MCP server straight into an agent gives it usage queries. Unblocked’s Context Engine reasons across those results and your other sources — following a Feature whose usage fell off to the UI change that moved it, the pull request behind that change, and the support ticket or Slack thread where customers asked where it went — and returns one cited answer.

Once connected, any MCP-compatible coding agent — Claude Code, Cursor, Devin, GitHub Copilot, Codex — reaches Pendo context through a single Unblocked MCP server connection.

What you get

• Live Page and Feature usage — Agents rank Pages, Features, and Track Events by usage and read one entity’s metrics from your Pendo subscription as they are right now.
• Visitor activity and developer logs — When a bug report names a visitor, agents can pull that visitor’s activity timeline and the console and network logs Pendo captured for the session.
• Read-only, tool-level control — Pendo’s write tools — creating feedback, editing segments, changing guide state — are never offered. Only read-only tools are available, and you choose which of them Unblocked may call. Change the selection anytime from Settings → Data Sources.
• Context Engine reasoning — Pendo results are reconciled with your code, pull requests, tickets, and conversations, so a change in how a feature is used leads to the release behind it — with citations.

Prerequisites

• An Unblocked account (free to start).
• Membership of a Pendo subscription where an admin has turned on the Pendo MCP server (read-only tools) under Settings → Subscription settings → AI access.
• An MCP-compatible coding agent (Claude Code, Cursor, Devin, etc.) to use the context in your editor.

Step 1: Connect Pendo to Unblocked

1. In Unblocked, go to Settings → Data Sources → Connect another data source, and under Data & Analytics select Pendo.
2. The Pendo MCP server URL is filled in for you. Choose OAuth, click Connect, and sign in to Pendo to authorize Unblocked.
3. Once Unblocked discovers the server’s tools, select the read-only tools it may use and click Save Settings.

Step 2: Install the Unblocked MCP server

On macOS or Linux, one command auto-detects and configures the supported agents on your machine:

On Windows, or when you prefer remote MCP, add the server manually using the configuration below, or follow the manual install guide .

claude mcp add -s user --transport http unblocked https://getunblocked.com/api/mcpsse

{
  "mcpServers": {
    "unblocked": {
      "url": "https://getunblocked.com/api/mcpsse"
    }
  }
}

https://getunblocked.com/api/mcpsse

Pendo hosts and maintains this MCP server. Unblocked calls only the read-only tools you select, at the moment a question needs them:

• listAllApplicationsLists the Pendo subscriptions and applications you can access.
• listCountablesLists or searches the Pages, Features, and Track Events defined in Pendo.
• aggregateEntityUsageRanks Pages, Features, or Track Events by usage.
• visitorActivityReturns one visitor’s chronological activity timeline.
• listGuidesLists or filters guides, optionally including their full content.
• devlogEventsReturns the developer console and network logs Pendo captured for a session.

To give Claude Code, Cursor, GitHub Copilot, Codex, or another MCP-compatible AI coding agent access to Pendo context, connect Pendo to Unblocked and add the single Unblocked MCP server to your agent.

Unblocked acts as the MCP context layer for your Pendo data, searching product usage, visitor activity, and guides alongside your other connected sources and returning cited results through these tools:

• context_researchResearches a question across your connected sources and calls the Pendo tools you selected when feature usage, guides, or visitor activity are relevant, returning a synthesized answer with citations.
• context_get_urlsFetches the full content behind URLs your agent encounters across connected sources — Jira, Linear, Notion, Confluence, Slack, GitHub, and more.

Questions you (or your agent) can ask Unblocked about your Pendo data:

• How much is the bulk export Feature used in Pendo, and which pull request added it?
• What did this visitor do before hitting the error in the support ticket, and do the session’s network logs show a failed request?
• Which Pendo guides point at the old settings page, and is there a Jira ticket for the settings redesign?
• Did usage of the reports Page change after last week’s release, and what shipped in it?