Pendo MCP tools for AI agents

Last updated: August 24, 2026 14:48

Model Context Protocol (MCP) tools let AI clients use your Pendo data, including metadata, product usage, guide performance, and feedback, to answer product questions. Tools return structured responses that are safe for automated workflows and agents like Claude or ChatGPT. While most tools are read-only, some allow you to write data back to Pendo, such as submitting feedback and updating ideas.

To connect your AI client to Pendo, follow the steps in Connect to the Pendo MCP server.

This article explains what's available in MCP by product area (which parts of Pendo agents can access) and by tool (what each one does, how to prompt it, and key limits).

Note: Metadata schema tools show the available fields for use in queries. Query tools return account or visitor data based on those fields. The fields included in query results depend on your subscription's available metadata and how your AI client constructs its request.

Some tools are used together to answer more complex questions. For example, listAllApplications can supply Application IDs for use in aggregateEntityUsage, and visitorMetadataSchema helps identify which metadata fields to include when constructing usage queries.

What you can access by product area

This table shows which Pendo product areas the MCP can access and which tools power each area. Use it to confirm whether an agent can see a given type of data before you design prompts or workflows around it.

Product area	What you can access by MCP	Key tools
Visitors and accounts	Metadata and counts, last activity, and segment-based cohorts	`visitorMetadataSchema`, `accountMetadataSchema`, `listVisitors`, `listAccounts`, `buildPendoSegment`
Segments	Segment retrieval and management, including creating, updating, and deleting saved segments	`getSegment`, `createSegment`, `updateSegment`, `deleteSegment`
Pages and Features	Usage metrics, including events, visitors, and accounts, ranked and time-series usage, and app-level usage	`productAreaMemberActivity`, `searchEntities`, `listProductAreas`, `listCountables`, `entityUsage`, `entityUsageTimeSeries`, `aggregateEntityUsage`, `appUsage`, `appUsageTimeSeries`
Agent Analytics	Key metrics, AI agents, use cases, issues, issue diagnosis, tracked issues, tracked use cases, and conversation-level analysis	`agentAnalyticsKeyMetrics`, `listAiAgents`, `listUseCases`, `listAiAgentIssues`, `agentAnalyticsIssueAnalysis`, `agentAnalyticsUseCaseAnalysis`, `listTrackedIssues`, `listTrackedUseCases`, `agentAnalyticsConversationAnalysis`, `agentAnalyticsTrackedIssueAnalysis`, `agentAnalyticsTrackedUseCaseAnalysis`
Guides and polls	Guide-level metrics, including views, completions, dismissals, poll activity, effectiveness, and categories	`searchEntities`, `listGuides`, `guidePollResponses`, `guideEffectivenessMetrics`, `aggregateGuideMetrics`, `guideUsage`, `listGuideCategories`, `listGuideOrdering`, `guideSet` `State`, `guideSetSegment`, `list` `GuideExperiments`
Sentiment surveys	NPS, CSAT, PMF, and UMUX scores, and individual survey responses	`listSurveys`, `surveyScores`, `surveyResponses`
Session Replay	Replay metadata and links with filters; frustration events, developer console logs, and network events	`sessionReplayList`, `devlogEvents`
Listen	Raw feedback, ideas, insights, clustered themes, submitting feedback, and creating and updating ideas and feedback	`getFeedbackItems`, `getFeedbackInsights`, `generateFeedbackTopics`, `getIdeas`, `createFeedbackItem`, `createIdeaItem`, `updateIdeaItem`, `updateFeedbackItem`, `linkIdeaAndFeedback`, `unlinkIdeaFeedback`
Orchestrate	Journey and email campaign discovery, configuration, journey step structure, and performance metrics	`listOrchestrateJourneys`, `getOrchestrateJourney`, `getOrchestrateJourneySteps`, `getOrchestrateJourneyMetrics`, `listOrchestrateEmails`, `getOrchestrateEmail`, `getOrchestrateEmailMetrics`, `listOrchestrateJourney` `Templates`, `createOrchestrateJourney` `FromTemplate`, `create` `OrchestrateJourneyFromJson`, `setOrchestrateJourneySchedule`
Command Center	Read your SaaS and AI app portfolio (both managed and discovered apps) with cost, licenses, owner, renewal date, category, AI and shadow-IT signals, IT governance status, and usage, and update editable fields on an app.	`commandCenterApps`, `updateCommandCenterApp`

Available MCP tools

The tables in this section list each externally available MCP tool, grouped by product area to match the table above, along with what each tool is for, example prompts, and important limits like date ranges and result thresholds. Use them as a reference when choosing tools or debugging why a question does or doesn't return data.

Foundational tools

These tools support other MCP tools by supplying IDs or looking up entities and segments. Use them first when you don't already have the information another tool needs.

Tool	What it's for	Example prompts	Why it's useful	Limits and availability
`listAll` `Applications`	Retrieve a list of subscriptions and applications you have access to. Often used as a first step with other tools (for example, passing App IDs to `aggregateEntity` `Usage` for usage data). Also confirms which application data you have access to through authentication.	List all apps in my subscription. Which apps belong to the Acme Co subscription? Use all App IDs to check top features by usage.	Provides the Subscription IDs and Application IDs needed for other tools.	Basic subscription and application information only; no subscription settings.
`searchEntities`	Find Pendo items by name or conceptual meaning, including Pages, Features, Track Events, accounts, and saved clips. (Deprecated for guides and product areas).	List all Pages that contain "/settings" in the URL pattern. Find every Feature that includes "export" in its name.	Helps you locate the Pages, Features, and events needed for building queries or exploring product usage.	Results ranked by relevance. Pages, Features, and Track Events are ordered by recency. Uses "fuzzy" matching when semantic similarity is low.
`segmentList`	List all publicly shared segments with their names and IDs.	List all the segments that contain "current customers" in the name. Which segment includes at-risk enterprise accounts?	Helps you identify available segments for use in other queries.	N/A
`getEntity`	Retrieve the full configuration of a single Page, Feature, Track Event, or guide by its exact ID. Returns URL rules for Pages, element rules and Page context for Features, event rules for Track Events, and ordered steps, polls, and interactive elements for guides. Doesn't return usage metrics.	Show me the URL rules for Page ID 12345. What steps are in guide abc-123?	Returns the complete configuration for one known entity, rather than the relevance-ranked results from `searchEntities`.	Find the entity ID first with `listCountables`, `listGuides`, or `searchEntities`.

Segments

These tools let you retrieve and manage saved segments from your AI client. They operate on the segments you have permission to view or edit, which includes your own private segments and any shared segments you can access. This is broader than the publicly shared segments returned by segmentList in the Foundational tools section.

Tool	What it's for	Example prompts	Why it's useful	Limits and availability
`getSegment`	Retrieve the full definition and details for a single saved segment by ID.	Get the definition for segment ID 12345. Show me how the @Enterprise segment is defined.	Returns the segment configuration so you can inspect targeting rules without opening Pendo.	Requires a segment ID. You can find one with `segmentList`.
`createSegment`	Create a new saved segment in Pendo.	Create a segment for visitors who used the export feature at least 3 times in the last 30 days and haven't completed onboarding. Save a new segment for Enterprise accounts renewed in the last 60 days.	Lets you build and save a reusable segment from your AI client.	Read-only users can't create shared segments.
`updateSegment`	Update an existing saved segment's definition or name.	Rename the @At-risk segment to @Churning. Update the @Trial-expiring segment to extend the window from 7 to 14 days.	Lets you revise segment definitions without leaving your AI client.	Requires a segment ID. Editing a shared segment you don't own requires the edit-shared-segment permission.
`deleteSegment`	Delete a saved segment by ID.	Delete the @Inactive-Q1 segment, it's no longer needed.	Keeps your segment library current without switching to Pendo.	Requires a segment ID. Deletion is permanent. It's rejected if the segment is referenced by a guide, compound segment, or saved report. Segments that back a feature flag must be managed through the feature-flag tools.

Visitors and accounts

Tool	What it's for	Example prompts	Why it's useful	Limits and availability
`accountMetadata` `Schema`	View the available metadata fields for accounts, such as ARR, industry, renewal date, or product tier. Returns field names, types (for example, boolean or string), and a historical flag indicating whether the field supports historical (event-time) filtering.	What metadata fields are available for accounts? Can I filter accounts by ARR or renewal date? What account attributes exist in our dataset?	Shows which account fields you can include in queries or use to filter data.	N/A
`visitorMetadata` `Schema`	View the available metadata fields for visitors, such as job title, CRM fields, region, or role. Returns field names, types (for example, boolean or string), and a historical flag indicating whether the field supports historical (event-time) filtering.	What metadata fields are available for visitors? List every Salesforce field we have at the visitor level. Which visitor fields are available for analyzing usage by role or onboarding status?	Helps you identify which visitor attributes you can use when filtering or organizing usage data.	N/A
`listAccounts`	List accounts matching an inline or saved segment.	How many accounts are in our @Enterprise segment, and what are their ARR values? List accounts up for renewal next month with their industry and renewal date.	Answers segment-composition questions more directly than a general account query.	N/A
`listVisitors`	List visitors matching an inline or saved segment.	How many visitors are in our trial-expiring segment?	Answers segment-composition questions for visitors, mirroring `listAccounts`.	N/A
`buildPendo` `Segment`	Build an inline AND/OR segment definition from visitor or account metadata, product usage (Pages, Features, Track Events), guide interactions, or existing segment membership, for use as an input to other tools.	Build a segment of visitors who used the export feature at least 3 times in the last 30 days. Create a segment for Enterprise accounts that haven't logged in for two weeks.	Lets you scope other tools, like `listAccounts`, `listVisitors`, `aggregateEntity` `Usage`, `queryFunnel`, `acquisition` `Trend`, and `cohortRetention` `Curve`, to a precise audience without creating and saving a segment in Pendo first.	The full segment definition must be provided in a single call; it can't be built incrementally across multiple requests. Time and date metadata values can be provided as Unix seconds or milliseconds, as required by the field schema, or as ISO 8601 dates and timestamps.
`visitorActivity`	Return a chronological activity timeline for one visitor.	Show me everything this visitor did in the app over the last week.	Supports debugging a specific visitor's journey rather than aggregate analysis.	Maximum date range: 31 days.

Pages and Features

Tool	What it's for	Example prompts	Why it's useful	Limits and availability
`productArea` `MemberActivity`	Return all Pages, Features, and Track Events belonging to a product area, including those with zero activity in the date range.	Which features in the Onboarding product area have zero usage this quarter? What pages in the Analytics product area should we consider sunsetting?	Helps you identify unused or low-engagement entities within a product area.	Maximum date range: 367 days.
`listProduct` `Areas`	List all product areas for a subscription, including their IDs, names, and descriptions. Supports optional fuzzy search and pagination.	What product areas do we have? List all product areas for this subscription. Show me all available product areas.	Helps you enumerate product areas or find a Product Area ID to pass to other tools that require it.	N/A
`listCountables`	List or search Pages, Features, and Track Events.	What Features exist in this app with "export" in the name? List all Track Events for our mobile app.	Helps you find the right entity before running a usage query, when you don't already know its exact name or ID.	N/A
`entityUsage`	Retrieve usage metrics for a single Page, Feature, or Track Event, broken down by visitor or account. You can also request visitor or account metadata fields to include with each result row.	How many visitors viewed the pricing page last month, broken down by account? Show me usage of the export Feature by visitor for the last 30 days, including each visitor's email and role.	Answers usage questions about one specific entity without configuring a broader activity query, and can add metadata context to the ranked visitor or account rows.	Maximum date range: 367 days. Use the `select` input with exact fields from `visitorMetadataSchema` when grouping by visitor or `accountMetadataSchema` when grouping by account. If `select` is omitted, metadata fields aren't returned.
`entityUsageTime` `Series`	Retrieve usage metrics for a single Page, Feature, or Track Event, bucketed by day, week, or month.	Show me weekly usage trends for the export Feature over the last quarter. How has traffic to the checkout page changed month over month this year?	Answers "how did usage change over time" questions for one entity, rather than a point-in-time total.	Maximum date range: 367 days.
`aggregateEntity` `Usage`	Rank all Pages, Features, or Track Events of a given type by usage.	What are the top 10 most-used Features this month? Which pages had the biggest drop in visitors compared to last quarter?	Answers cross-entity ranking questions without building a custom aggregation.	Maximum date range: 367 days.
`appUsage`	Retrieve app-level usage metrics, broken down by visitor or account. Optionally return requested visitor or account metadata fields with each row.	Show me app usage broken down by account for the last 30 days, including ARR and company size.	Provides an app-wide usage view without scoping to one Page or Feature, and can add metadata context to the ranked visitor or account rows.	Maximum date range: 367 days. Use the `select` input with exact fields from `visitorMetadataSchema` when grouping by visitor or `accountMetadataSchema` when grouping by account. If `select` is omitted, metadata fields aren't returned.
`appUsageTime` `Series`	Retrieve app-level usage metrics over time, bucketed by day, week, or month.	How has overall app engagement trended over the past 6 months?	Shows app-level usage trends, complementing the point-in-time totals from `appUsage`.	Maximum date range: 367 days.
`productEngagement` `Score`	View product health using Pendo's Product Engagement Score (PES) for adoption, stickiness, and growth. Supports custom configurations for user base, stickiness calculations, and event filters.	What's our PES for the last 30 days? Calculate adoption for our top five Features. What's our stickiness score for accounts, weekly over monthly?	Provides adoption, stickiness, and growth metrics for a complete view of product health and engagement.	Maximum date range: 180 days.
`queryFunnel`	Calculate an ordered two- or three-step unique-visitor funnel.	What's our conversion rate from signup to first project created to first invite sent?	Answers drop-off and completion questions for a defined, ordered flow.	N/A
`acquisition` `Trend`	Measure first-time visitors or accounts by period.	How many new accounts did we acquire each month this year?	Provides a growth-tracking view, separate from retention.	Maximum date range: 367 days.
`cohortRetention` `Curve`	Build a retention curve for an app, Page, Feature, Track Event, or product area. For a product area, a visitor or account is active when they use any Page, Feature, or Track Event in the area; guide activity isn't counted. For event and product area scopes, an app ID is optional and can be used to narrow a multi-app result.	What does retention look like for accounts that signed up in Q1?	Provides standard retention-curve analysis without a custom query.	Maximum date range: 367 days.

Agent Analytics

Tool	What it's for	Example prompts	Why it's useful	Limits and availability
`agentAnalytics` `KeyMetrics`	Retrieve key aggregate metrics for an AI agent's conversations, including prompt volume, visitor and account counts, rage prompt rates, and retention.	How many conversations has my support agent had in the last 30 days? What's the rage prompt rate for our onboarding agent this month? Show me key metrics and trends for my chat agent over the past two weeks.	Provides a high-level summary of agent performance and engagement trends without requiring you to build a custom report.	Maximum date range: 90 days.
`listAiAgents`	Retrieve a list of all AI agents you have access to. Often used as the first step to get Agent IDs for use with other Agent Analytics tools.	List all AI agents in my subscription. What agents are configured for my app?	Provides the agent IDs needed to run queries.	N/A
`listUseCases`	Retrieve conversation clustering analysis for an AI agent, grouping prompts and conversations by semantic topic.	What topics are visitors asking our support agent about most? Show me the top use cases for our onboarding agent last quarter.	Helps you understand what visitors are actually trying to do with your AI agent, without reading individual conversations.	Maximum date range: 90 days. Requires an App ID and an Agent ID from `listAiAgents`.
`listAiAgent` `Issues`	Retrieve detected issues in AI agent conversations.	What problems are users running into with our support agent? Show me the most common issues in our chat agent over the last 30 days. Have we seen fewer incorrect answer issues since last month?	Surfaces patterns of failure or frustration in AI agent conversations so you can prioritize improvements.	Maximum date range: 90 days. Limited to 500 issues; narrow by Agent ID or date range if needed.
`agentAnalytics` `IssueAnalysis`	Retrieve issue diagnoses, flagged response tool and model usage, and visitor prompt content for the events of a specific detected issue cluster.	What patterns exist among instances of the "incorrect answers" issue? Which tools were called in instances of the "timeout error" issue? Show me what users said in conversations flagged as the "authentication failure" issue.	Helps you understand why conversations were flagged, see patterns in visitor prompts, and identify which tools and models were involved.	Maximum date range: 90 days. Requires an Agent ID, conversation IDs, and event IDs from `listAiAgent` `Issues`.
`agentAnalytics` `UseCaseAnalysis`	Perform a detailed analysis of one emergent (automatically clustered) use case identified by `listUseCases`.	Tell me more about the "password reset" use case cluster.	Goes beyond the summary in `listUseCases` into the specifics of one cluster, the same way `agentAnalytics` `IssueAnalysis` expands on `listAiAgent` `Issues`.	Maximum date range: 90 days. Requires Agent Analytics.
`listTracked` `Issues`	List user-defined tracked issues for an AI agent.	What tracked issues have we set up for this agent?	Gives you the tracked issue IDs needed to run `agentAnalytics` `TrackedIssue` `Analysis`.	Maximum date range: 90 days. Requires Agent Analytics.
`listTrackedUse` `Cases`	List user-defined tracked use cases for an AI agent.	What tracked use cases exist for this agent?	Gives you the tracked use case IDs needed to run `agentAnalytics` `TrackedUseCase` `Analysis`.	Maximum date range: 90 days. Requires Agent Analytics.
`agentAnalytics` `Conversation` `Analysis`	Perform a detailed analysis of selected AI agent conversations.	Show me the conversations with the most rage prompts this week.	Surfaces specific problem conversations for deeper review, beyond the aggregate view in `agentAnalytics` `KeyMetrics`.	Maximum date range: 90 days. Requires Agent Analytics and conversation IDs.
`agentAnalytics` `TrackedIssue` `Analysis`	Perform a detailed analysis of one tracked issue, including sampled visitor prompts and tool or model usage.	Give me more detail on the checkout failure tracked issue.	Supports root-cause analysis for a known, recurring issue.	Maximum date range: 90 days. Requires an Agent ID and a tracked issue ID from `list` `Tracked` `Issues`.
`agentAnalytics` `TrackedUseCase` `Analysis`	Perform a detailed analysis of one tracked use case.	Give me more detail on the billing questions tracked use case.	Supports root-cause and pattern analysis for a known, recurring use case.	Maximum date range: 90 days. Requires an Agent ID and a tracked use case ID from `list` `Tracked` `UseCases`.

Command Center

Command Center MCP tools are turned off by default. To turn them on for your subscription, contact Pendo Support.

Tool What it's for Example prompts Why it's useful Limits and availability

commandCenter
Apps

List the Command Center SaaS portfolio, covering both managed and discovered apps, with each app's cost, estimated cost, license count, owner, renewal date, category, AI and shadow-IT signals, admin notes, IT governance status, active-user count, license usage, and potential annual savings from unused licenses.

What's our total SaaS and AI portfolio spend, and how has it changed over time?

Which apps are over-licensed based on low utilization, and how much spend could we reclaim?

Which apps renew in the next 90 days, and what does utilization look like for each?

Which AI tools and agents are employees using, and with which vendors?

Gives a single view of SaaS spend, license waste, and shadow-IT and AI risk without leaving your AI client.

Requires Command Center.

Discovered apps appear only if they had activity in the date range. Potential savings are shown only when license usage is 60% or lower, an annual cost is available, and license count is positive.

Distinguishes verified costs from estimated costs, and flags apps whose usage may be undercounted (for example, mobile-, desktop-, or API-only apps that browser-based discovery can't fully capture).

updateCommand
CenterApp

Update an app's license count, annual cost, renewal date, or notes (individually or several at once) for a single managed or discovered app.

Set the license count for [app name] to 50.

Update the annual cost of [app name] to $12,000.

Set the renewal date for [app name] to January 31, 2027.

For [app name], set licenses to 50, cost to $12,000, and the renewal date to January 31, 2027 in one go.

Keeps app records (licenses, costs, renewals, and notes) current directly from your AI client.

Write tool. A subscription admin must enable write tools in Settings > Subscription settings > AI access, and read-only tools must be enabled first.

Requires Command Center. Applies only to apps you have permission to edit, and each change requires your confirmation before it's applied.

Setting a cost marks it as verified. Notes replace the existing note in full (send an empty value to clear). Renewal date uses YYYY-MM-DD (send an empty value to clear).

Owner, category, IT status, and shadow-IT classification are read-only through MCP and are managed in the Pendo product.

Guides and polls

Tool	What it's for	Example prompts	Why it's useful	Limits and availability
`listGuides`	List, filter, and optionally retrieve full content for in-app guides, including IDs, names, states, types, and scheduling.	List all public guides. Show me draft guides. Which guides are set to launch automatically? List guides that have expired. Show me all tooltip guides that are currently staged. What does the "Onboarding tour" guide say to users?	Helps you find guides by status, type, activation method, or other attributes, and review full content for specific guides when needed.	Supports search on guide names and descriptions using semantic or "fuzzy" matching. Can return either summary lists of guides or full content for a single guide; full content is available for eligible guides only.
`guidePoll` `Responses`	Analyze poll responses collected in a guide.	What were the responses to the poll in our onboarding guide?	Answers poll-specific questions that survey-score tools don't cover.	N/A
`guideEffectiveness` `Metrics`	Return dashboard-consistent guide engagement, completion, and goal-adoption rates, with filtering and segment comparison.	How are our onboarding guides performing compared to feature announcement guides? Compare guide performance across our Enterprise and SMB segments.	Mirrors the data in the Effectiveness tab in Guides, including views, visitors, goal adoption, engagement, and completion, without opening Pendo.	Requires Guides Pro.
`aggregateGuide` `Metrics`	Rank guides by views, completions, dismissals, unique visitors, unique accounts, or views per user. You can restrict results by guide IDs, current status, guide type, activation method, product area, guide category, Page, or app.	Which guides had the most completions last quarter? Rank our onboarding guides by engagement rate.	Answers cross-guide ranking questions. Use `guideEffectiveness` `Metrics` instead for dashboard-consistent metrics on a smaller, filtered set of guides.	N/A
`guideUsage`	Break down usage of a single guide by visitor or account, or inspect each guide step's visitor count and time on step.	Show me a breakdown of who's completed the new user onboarding guide.	Provides a deep-dive into one guide's audience, rather than a cross-guide comparison.	N/A
`listGuide` `Categories`	Return the guide-category tree for a subscription.	What guide categories do we have set up?	Supports discovery of category values to filter by in `guideEffectiveness` `Metrics`.	N/A
`listGuideOrdering`	Return guide display-order rules for an application.	What's the display order for guides on our web app?	Helps diagnose why a guide isn't showing when other guides are also eligible.	N/A
`guideSet` `State`	Change the state of a guide, such as publishing a draft, staging a guide for review, or making an active guide inactive.	Publish the "New feature announcement" guide. Make the onboarding tour inactive while we update the content.	Lets you manage guide states from your AI client without opening the Guides builder.	Valid states are draft, staged, public (live to end users), and inactive. Requires a Guide ID.
`guideSet` `Segment`	Update the audience segment targeting for a guide.	Change the "Onboarding tour" guide to target the @New-users segment instead of Everyone. Update the "Upgrade prompt" guide to only show to @Trial accounts.	Lets you retarget a guide without opening the Guides builder.	Requires a Guide ID. Accepts either a saved segment ID or an inline segment definition built with `buildPendoSegment`.
`listGuide` `Experiments`	List A/B experiments configured on guides, including their status and configuration.	What guide experiments are currently running? List all experiments on the onboarding tour guide. Which guide experiments are in draft?	Gives you a view of active and draft guide experiments so you can review what's being tested without opening Pendo.	The guide filter is optional; omit it to return all experiments. Requires Guides with experiments enabled.

Sentiment surveys

Tool	What it's for	Example prompts	Why it's useful	Limits and availability
`listSurveys`	List available surveys, including their names, types, and IDs.	What surveys are set up in our subscription? List all NPS surveys. Which CSAT surveys are active?	Gives you the Survey IDs needed before running `surveyScores` or `surveyResponses`.	N/A
`surveyScores`	Return NPS, CSAT, PMF, and UMUX scores by survey and type.	What's our NPS and CSAT score for the last quarter?	Pulls sentiment data across all survey types in one tool, instead of needing a separate tool per type.	Requires NPS for NPS scores; requires Sentiment for CSAT, PMF, and UMUX scores.
`surveyResponses`	Return per-visitor responses for a single survey, including individual answers, response distributions per question, and each visitor's most recent answer.	What did visitors answer on the CSAT survey "my-csat-survey"?	Pulls raw per-visitor answers in one call, pivoted into one row per visitor with a column per question, including guide polls.	Requires NPS for NPS responses; requires Sentiment for CSAT, PMF, and UMUX responses.

Session Replay

Tool What it's for Example prompts Why it's useful Limits and availability

sessionReplay
List

Returns links to replays for specific visitors or behaviors.

Default filters: minimum duration 120 seconds, minimum activity 5%. Exclude list behavior options available. Supports event property filtering.

Use the optional event
Properties parameter to narrow results to sessions where a specified page, feature, or track event was captured with matching historical metadata values.

Show me replays from the last week with high activity.

Show me sessions with frustration events in the onboarding flow.

Show me replays where users visited the error page.

Show me replays where the checkout-completed Track Event occurred.

Show me replays for the Onboarding product area.

Show me replays where the checkout-completed Track Event occurred with plan_type = enterprise.

Helps you find high-value sessions to review, making it easier to identify friction or unexpected user behavior.

Maximum of 50 replays for each query.

Maximum date range: 31 days.
Replay content not exposed through the MCP.

devlogEvents

Retrieve raw development logs for a visitor or session, including HTTP request and response details, log levels, messages, and stack traces so you can see exactly what happened technically during the experience.

Use these logs to understand which errors visitors encountered in the session and why.

Show me devlogs for this replay: [link]

Show network requests captured in clip [link]

What HTTP errors occurred during visitor john's session?

Get devlogs for clip ID abc-123

What API calls did this visitor make during their session?

Helps you investigate developer console logs, network errors, or HTTP activity captured during a replay.

Requires a clip ID or replay URL.

Maximum of 100 events for each query.

Maximum date range: 367 days.

Listen

Tool	What it's for	Example prompts	Why it's useful	Limits and availability
`getFeedback` `Items`	Retrieve raw customer feedback items that match specific filters, including the original title, description, status, and creation date, along with associated account and visitor details. Filter by account types, alerts, feedback types, product areas, and more.	Show all feedback items from enterprise accounts about onboarding. List raw feedback for accounts in the @At-risk segment from the last 30 days. Get all feedback where the title or description mentions "performance".	Returns the full, unprocessed feedback so you can review exact customer language and context without relying on summaries or extracted insights.	Maximum of 30 feedback items for each call. Raw feedback only.
`getFeedback` `Insights`	Retrieve extracted feedback insights from customer feedback that match specific filters, including summaries, explanations, and supporting quotes. Filter by account types, alerts, feedback types, product areas, and more.	Summarize the main feedback insights from customers on our new reporting page. Show feedback insights about reliability issues from the last quarter. List top insights from feedback submitted by enterprise customers.	Helps you quickly understand key themes and takeaways from customer feedback without reading every individual feedback item.	Summaries and topics only, not full dataset. May require multiple calls for large date ranges.
`generateFeedback` `Topics`	Generate AI-clustered topics from customer feedback that matches specific filters, with each topic including a name, description, and count of related insights. Filter by account types, alerts, feedback types, product areas, and more.	Generate topics from all feedback about onboarding in the last 90 days. Show the main themes in feedback from customers who recently downgraded. Cluster feedback about performance issues into topics.	Provides a high-level view of the most common feedback themes to support prioritization and trend analysis.	Summaries and topics only, not full dataset. May require multiple calls for large date ranges.
`getIdeas`	Retrieve product ideas that match specific filters. Each item includes a title, description, and status. Supports the same filters as other feedback tools, including account types, product areas, date range, and search terms.	What ideas have been submitted about our onboarding experience? Show me ideas about analytics submitted in the last quarter.	Helps you quickly surface and review product ideas alongside feedback without leaving your AI client.	Maximum of 30 items for each call.
`createFeedback` `Item`	Create a new feedback item in Listen.	Log a feature request for dark mode support. Submit feedback that the export CSV button is confusing. Capture this bug report about broken pagination.	Allows you to submit product feedback, feature requests, or bug reports directly from your AI client.	Requires an App ID, title, description, and at least one Visitor ID or Account ID.
`createIdea` `Item`	Create a new idea in Listen.	Create an idea for a bulk export option.	Lets you capture a product idea directly from your AI client.	Requires a title.
`updateIdeaItem`	Update an existing Listen idea.	Mark the bulk export idea as In Progress.	Lets you maintain idea records without leaving your AI client.	Requires an idea ID.
`updateFeedback` `Item`	Update an existing feedback item.	Update this feedback item's status to Reviewed.	Lets you triage feedback items conversationally.	Requires a Feedback ID.
`linkIdeaAnd` `Feedback`	Associate an existing idea with an existing feedback item.	Link this feedback item to the dark mode idea.	Keeps feedback and ideas connected without a manual step in Listen; propagates votes from the feedback item to the idea.	Requires an idea ID and a feedback item ID.
`unlinkIdea` `Feedback`	Remove the association between an idea and a feedback item.	Unlink this feedback item from that idea, it was linked by mistake.	Corrects mistaken links without deleting either record.	Requires an idea ID and a feedback item ID.

Orchestrate

Tool	What it's for	Example prompts	Why it's useful	Limits and availability
`listOrchestrate` `Journeys`	List Orchestrate journeys in a subscription, optionally filtered by status (draft, review, scheduled, active, paused, completed, or disabled). Use it to find a Journey ID before requesting configuration, steps, or performance.	List all active Orchestrate journeys. What journeys are currently paused? Show me our scheduled journeys.	Gives you the Journey IDs and lifecycle status you need before drilling into a specific journey.	Requires Orchestrate. "Scheduled" means an active journey with a future start date. No step-level detail or metrics; use `getOrchestrate` `JourneySteps` and `getOrchestrate` `JourneyMetrics`.
`getOrchestrate` `Journey`	Retrieve full configuration for a single journey by ID, including audience, goal, scheduling, and email settings.	Show me the configuration for journey 12345. What's the audience and goal for this journey?	Confirms how a journey is targeted and scheduled without opening it in Orchestrate.	Doesn't include the step graph (use `getOrchestrate` `JourneySteps`) or performance metrics (use `getOrchestrate` `JourneyMetrics`). Requires a Journey ID from `listOrchestrate` `Journeys`.
`getOrchestrate` `JourneySteps`	Retrieve the ordered step graph for a journey, including each step's type (message, condition, or exit), position, and linked email or guide.	What steps are in this journey? Which emails does this journey send, and in what order?	Shows a journey's structure so you understand the sequence and branches before reviewing performance.	Structure only. Doesn't include per-step send, open, or click metrics. For journey performance, use `getOrchestrate` `JourneyMetrics`. Requires a Journey ID.
`getOrchestrate` `JourneyMetrics`	Retrieve journey-level performance, including visitors entered, visitors completed, and goal attainment for journeys with a goal.	How is journey 12345 performing? What's the goal attainment rate for our onboarding journey? How many visitors entered and completed this journey last month?	Answers how a journey is doing overall without building a report in Orchestrate.	Journey-wide aggregates only; no per-step or per-visitor breakdown. Maximum date range: 367 days. Date range is optional (provide both start and end, or neither); goal metrics are cumulative totals and aren't returned when a date range is set. Visitors completed reflects exiting the journey or aging out, which is a different count than goal attainment.
`listOrchestrate` `Emails`	List Orchestrate email campaigns, both standalone and journey-linked (Listen and Sentiment survey emails excluded). Supports optional filters for status, app, or name.	List all standalone emails. What emails are in draft? Find emails with "welcome" in the name.	Gives you the Email IDs and lifecycle timestamps you need before looking up configuration or metrics for a specific email.	Requires Orchestrate. List rows don't include which journey an email belongs to; use `getOrchestrate` `Email` for that.
`getOrchestrate` `Email`	Retrieve full configuration for a single email by ID, including subject, provider, audience, schedule, and (for journey-linked emails) its Journey ID.	Show me the configuration for email 12345. What's the subject line and sender for this email?	Confirms an email's setup, including whether it sends through Pendo or a third-party provider (HubSpot, Marketo, or Eloqua).	Requires an Email ID from `list` `Orchestrate` `Emails`.
`getOrchestrate` `EmailMetrics`	Retrieve performance metrics for a single email, including delivery, unique opens, unique clicks, bounces, unsubscribes, and spam complaints, matching the Orchestrate email overview.	How did email 12345 perform last month? What's the open rate and click rate for this email? Show delivery and bounce rates for this email between June 1 and June 30.	Answers how an email performed, including emails sent through a third-party provider (HubSpot, Marketo, or Eloqua), which return the same metrics as Pendo-sent emails.	Email-level aggregates only; doesn't identify which visitors opened, clicked, bounced, or unsubscribed. Maximum date range: 367 days. Requires an Email ID from `list` `Orchestrate` `Emails`.
`listOrchestrate` `JourneyTemplates`	List the available journey templates you can use to create new journeys.	What journey templates are available? Show me templates for onboarding journeys.	Gives you the Template IDs and names needed before creating a journey with `createOrchestrateJourneyFromTemplate`.	Requires Orchestrate.
`createOrchestrate` `JourneyFromTemplate`	Create a new draft journey in Orchestrate from an existing template.	Create a new onboarding journey from the "30-day trial" template. Use the welcome-series template to create a journey for new Enterprise accounts.	Lets you start a journey from a known template without building it step by step.	Requires Orchestrate and a Template ID from `listOrchestrateJourneyTemplates`. The journey is created in a draft state.
`createOrchestrate` `JourneyFromJson`	Create a new draft journey in Orchestrate from a full JSON journey definition.	Create a journey from this JSON configuration: [paste JSON]. Build a new 3-step email journey using this definition.	Supports advanced journey creation and automation workflows where the full journey structure is known or generated programmatically.	Requires Orchestrate. The supplied journey definition must be valid. The journey is created in a draft state.
`setOrchestrate` `JourneySchedule`	Set or update the schedule for a journey, including its start and end dates.	Schedule the onboarding journey to start on September 1. Set an end date of December 31 for the renewal journey.	Lets you control when a journey runs from your AI client without reopening it in Orchestrate.	Requires Orchestrate and a Journey ID from `listOrchestrateJourneys`.