Merge Unified's Pendo integration Merge Agent Handler's Pendo MCP server

Connect your AI Agents to Pendo in minutes

Merge lets you securely connect your agents to Pendo and thousands of tools instantly

Start building for free

Read docs

Pendo

Learn more about Merge Agent Handler

Available tools

get_account_metadata_schema

View available metadata fields for Pendo accounts, including field names and types. Use this to discover what metadata fields can be queried or written.

query_accounts

Retrieve Pendo account records matching metadata criteria. Max 50,000 results. Use offset for pagination.

get_account

Get a single Pendo account by ID. Returns all metadata fields. Use query_accounts to search for account IDs.

bulk_delete_accounts

Delete up to 500 Pendo accounts and all their associated data. Use for GDPR right-to-erasure requests. Use query_accounts to find account IDs.

upsert_account_metadata

Set custom metadata fields on a Pendo account. Pass metadata as a dict of field names to values. Use query_accounts to find valid account IDs.

query_activity

Query Pendo usage metrics by source: pageEvents, featureEvents, guideEvents, trackEvents, or pollEvents. Defaults to last 90 days. Pass starttime/endtime (epoch ms) to override. Max 367-day range. Max 1,000 records per call.

get_product_area_activity

Get page view activity for all pages in a Pendo product area. Max 367-day range. Defaults to last 90 days. Use offset for pagination. Max 10,000 records per call.

search_entities

Find Pendo items (Pages, Features, Track Events, guides) by name substring. Returns items whose names contain the query string (case-insensitive). Filter by entity_types to narrow results. Results are capped at 1,000 items per entity type.

list_segments

List all publicly shared Pendo segments with names and IDs. Segments define visitor/account cohorts for use in other queries.

list_pages

List all tagged pages in Pendo with their IDs, names, and URL rules. Use get_page to retrieve full details for a specific page. Use offset for pagination.

get_page

Get a single Pendo page definition by ID, including URL rules and app association. Use listpages or searchentities to find page IDs.

list_features

List all tagged features (click targets) in Pendo with their IDs, names, and selectors. Use get_feature to retrieve full details for a specific feature. Use offset for pagination.

get_feature

Get a single Pendo feature definition by ID, including CSS selector and page association. Use listfeatures or searchentities to find feature IDs.

list_track_types

List all custom track event types instrumented in Pendo. Returns event names and IDs needed before querying trackEvents in query_activity. Use offset for pagination.

list_guides

List Pendo guides, optionally filtered by state or type. Returns ID, name, description, state, and scheduling info. Use offset for pagination. Max 1,000 guides per call.

get_guide

Get a single Pendo guide by ID. Returns full definition including steps, targeting, and scheduling. Use list_guides to find valid guide IDs.

get_guide_metrics

Get performance data for a Pendo guide: views, completions, dismissals. Max 93-day range. Defaults to last 90 days. Counts are based on up to 10,000 raw events — results may be underreported for high-volume guides. Use list_guides to find guide IDs.

validate_credential

Validate Pendo credentials by querying the visitors pipeline. Returns success and message.

get_visitor_metadata_schema

View available metadata fields for Pendo visitors, including field names and types. Use this to discover what metadata fields can be queried or written.

query_visitors

Retrieve Pendo visitor records matching metadata criteria. Max 50,000 results. Always excludes anonymous visitors. Use offset for pagination.

get_visitor

Get a single Pendo visitor by ID. Returns all metadata fields. Use query_visitors to search for visitor IDs.

bulk_delete_visitors

Delete up to 500 Pendo visitors and all their associated events. Use for GDPR right-to-erasure requests. Use query_visitors to find visitor IDs.

upsert_visitor_metadata

Set custom metadata fields on a Pendo visitor. Pass metadata as a dict of field names to values. Use query_visitors to find valid visitor IDs.

View all tools by creating a free account See more tools

How to set up Merge Agent Handler

In an mcp.json file, add the configuration below, and restart Cursor.

Learn more in the official documentation ↗

1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11

Copy Code

Open your Claude Desktop configuration file and add the server configuration below. You'll also need to restart the application for the changes to take effect.

Make sure Claude is using the Node v20+.

Learn more in the official documentation ↗

1{
2  "mcpServers": {
3    "agent-handler": {
4      "command": "npx",
5      "args": [
6        "-y",
7        "mcp-remote@latest",
8        "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
9        "--header",
10        "Authorization: Bearer ${AUTH_TOKEN}"
11      ],
12      "env": {
13        "AUTH_TOKEN": "yMt*****"
14      }
15    }
16  }
17}

Copy Code

Open your Windsurf MCP configuration file and add the server configuration below.
Click on the refresh button in the top right of the Manage MCP server page or in the top right of the chat box in the box icon.

Learn more in the official documentation ↗

1{
2    "mcpServers": {
3      "agent-handler": {
4        "command": "npx",
5        "args": [
6          "-y",
7          "mcp-remote@latest",
8          "https://ah-api.merge.dev/api/v1/tool-packs/<tool-pack-id>/registered-users/<registered-user-id>/mcp",
9          "--header",
10          "Authorization: Bearer ${AUTH_TOKEN}"
11        ],
12        "env": {
13          "AUTH_TOKEN": "<ah-production-access-key>"
14        }
15      }
16    }
17  }

Copy Code

In Command Palette (Cmd+Shift+P on macOS, Ctrl+Shift+P on Windows), run "MCP: Open User Configuration".

You can then add the configuration below and press "start" right under servers. Enter the auth token when prompted.

Learn more in the official documentation ↗

1{
2  "inputs": [
3    {
4      "type": "promptString",
5      "id": "agent-handler-auth",
6      "description": "Agent Handler AUTH_TOKEN", // "yMt*****" when prompt
7      "password": true
8    }
9  ],
10  "servers": {
11    "agent-handler": {
12      "type": "stdio",
13      "command": "npx",
14      "args": [
15        "-y",
16        "mcp-remote@latest",
17        "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
18        "--header",
19        "Authorization: Bearer ${input:agent-handler-auth}"
20      ]
21    }
22  }
23}

Copy Code

FAQs on using Merge's Pendo MCP server

What is a Pendo MCP?

It's an MCP server that exposes your Pendo product analytics data and functionality to AI agents via tools. Your agents can invoke these tools to query visitor and account records, analyze feature adoption, retrieve guide metrics, search segments, and more.

Pendo offers an official MCP server, but you can also use one from a third-party platform, like Merge Agent Handler.

How can I use the Pendo MCP server?

The use cases naturally depend on the agent you've built, but here are a few common ones:

Churn risk detection: An agent queries Pendo activity data for accounts that have dropped below a usage threshold in the past 30 days, cross-references those accounts with open renewals in Salesforce, and posts a prioritized list to the customer success Slack channel each Monday morning

Onboarding completion monitoring: When a new account is created in your CRM, an agent tracks that account's guide completion rate in Pendo and sends a follow-up task to the assigned CSM in Asana once the account finishes the onboarding sequence

Feature adoption reporting: A product manager asks their AI to pull feature engagement data from Pendo for the past quarter, compare it across user segments, and generate a structured summary for the weekly product review meeting

Guide targeting updates: When a support ticket volume spikes around a particular feature, an agent identifies the relevant Pendo guide, retrieves its current audience rules, and flags it for the product team to update targeting or content

What are popular tools for Pendo's MCP server?

Here are some of the most commonly used tools:

query_accounts: retrieves a list of accounts from Pendo filtered by metadata fields or usage criteria. Useful for agents that need to segment accounts by plan type, activity level, or custom properties before taking action

query_visitors: fetches visitor records based on behavioral or metadata filters. Call this when an agent needs to identify specific users, such as those who have not completed a key workflow or who match a target persona

query_activity: returns event-level activity data for visitors or accounts over a time range. Good for agents tracking feature engagement trends or detecting drops in product usage

get_guide_metrics: returns performance data for a specific Pendo guide, including views, completions, and dismissals. Helpful when an agent needs to evaluate whether an in-app guide is driving the intended behavior

list_segments: returns all defined audience segments in Pendo. Use this when an agent needs to find the right segment before scoping a usage query or updating guide targeting

get_feature: retrieves metadata and engagement stats for a specific tracked feature. Call this when an agent is generating adoption reports or investigating whether users are discovering a particular capability

What makes Merge Agent Handler's Pendo MCP server better than alternative Pendo MCP servers?

There are several reasons to choose Merge Agent Handler's Pendo MCP server over building your own or using another option:

Enterprise-grade security and DLP: Merge Agent Handler includes built-in data loss prevention controls that let you block or redact sensitive fields before they reach an agent. For Pendo, this means you can prevent individual visitor identifiers, account-level revenue data, and proprietary usage patterns from being exposed even when the agent has broad read access

Managed authentication and credentials: Merge stores and refreshes Pendo credentials on your behalf. You never expose raw API keys or OAuth tokens to an agent or manage token rotation manually

Real-time observability and audit trail: Every tool call made against Pendo is logged with timestamp, tool name, input parameters, and response metadata. You can audit exactly what an agent read or wrote without instrumenting anything yourself

Tool Packs and controlled access: Tool Packs let you bundle specific Pendo tools with tools from other connectors into a single MCP endpoint, scoped to a specific use case. An agent gets exactly the tools it needs, nothing more

How can I start using Merge Agent Handler's Pendo MCP server?

You can take the following steps:

1. Create or log into your Merge Agent Handler account.

2. Install the Merge CLI by running pipx install merge-api, then run merge configure to link the CLI to your Merge account and merge login to authenticate your session.

3. Register the Agent Handler MCP server with Claude Code by running claude mcp add --transport http agent-handler https://ah-api.merge.dev/mcp, then open Claude Code and run /mcp to confirm agent-handler appears with a connected status.

4. Select agent-handler from the MCP list. This opens a browser window where you select which integrations to authenticate. Choose Pendo and complete the auth flow. Merge stores and manages the credentials going forward.

5. Open a Claude Code session and start querying Pendo data directly. The first time you use a Pendo tool, a Magic Link may appear to complete connector authentication.

If you want to connect Merge Agent Handler's Pendo MCP with internal or customer-facing agentic products, you can follow the steps in our docs.

Can employees use Merge to connect their AI tools to Pendo?

Yes, Merge for Workforce lets your employees connect Claude, ChatGPT, Microsoft Copilot, Cursor, and other MCP-compatible AI tools to Pendo without bypassing IT governance.

Instead of setting up direct connections with personal credentials that IT can't monitor or revoke, each employee authenticates through Merge and gets individual credentials tied to their identity. A product manager, for instance, can ask their AI to pull feature adoption data, query a visitor segment, or retrieve guide performance metrics, all within the permissions IT has defined.

IT also provisions access by role or group via SCIM. A customer success manager, for example, gets Pendo access to monitor account usage trends, Salesforce to track renewal health, and Slack to flag at-risk accounts with the team; while a product analyst gets Pendo access to query visitor activity and segment data, Looker to build adoption dashboards, and Jira to link usage findings to roadmap tickets.

Every tool call an employee's AI makes to Pendo is also inspected against your DLP rules and logged to a searchable audit trail, giving security teams full visibility into what data was accessed and by whom.