# Pendo (US1) MCP connector

The Pendo (US1) connector brings your Pendo accounts, visitors, segments and product usage from the US1 region to Claude, ChatGPT, Cursor and any MCP client, so your team can ask about adoption and build segments in plain language.

Source: https://elaichi.ai/connectors/pendo-us1/

## Facts

| | |
| --- | --- |
| Application | Pendo (US1) |
| Category | Analytics |
| AI tools | 87 |
| Authentication | Connects over OAuth |
| Bring your own OAuth app | No |
| Native MCP | Yes. Pendo (US1) builds and runs this MCP server. Elaichi adds sign-in, access controls and an audit log on top |
| Support for its tools | support.pendo.io/hc/en-us |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once Pendo (US1) is connected

- Which accounts dropped in usage over the last 30 days?
- Build a segment of visitors who used Reports this month.
- Show the product engagement score for our enterprise accounts.

## Connect Pendo (US1) in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick Pendo (US1).
2. Optionally set Share with, then press Connect.
3. Approve it in Pendo (US1). Pendo (US1)'s own window opens. Whoever approves it decides what this connection can reach.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Pendo (US1) tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Pendo (US1) MCP connector for Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## Pendo (US1) MCP connector for ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web today. The plugin directory lives at chatgpt.com/plugins.

## Pendo (US1) MCP connector for Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## Connect Pendo (US1) to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Only Read is granted by default, which is not enough to call a Pendo (US1) tool. Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Grant Read and Run tools. Think hard before granting Delete, which reaches into connected apps and cannot be undone.

## What teams do with Pendo (US1) through Elaichi

### See which features an account really uses

Product. Ask how a specific account used each product area over the last quarter and get the usage trend back as a plain answer. No dashboard to build first.

### Check account activity before a renewal call

Customer Success. Pull an account's recent activity, its engagement score and the visitors who have gone quiet, then walk into the call knowing where adoption stands.

### Find what a visitor did before writing in

Support. Look up the visitor who opened the ticket and see which parts of the product they touched and when, so the reply speaks to what actually happened.

### Build a segment for the next campaign

Marketing. Describe the audience in words, such as accounts that adopted one feature but not another, and have the segment created in Pendo ready to use.

### Pull the product engagement score every Monday

Leadership. Ask for the product engagement score and app usage across all applications, broken down by week, and get the numbers without waiting on an analyst.

### Compare usage across target accounts

Sales. Before a quarterly review, line up usage for the accounts in a territory and see which ones are growing and which have stalled.

## Elaichi vs Zapier MCP vs Composio for Pendo (US1)

All three can connect Pendo (US1) to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

| What to check | Elaichi | Zapier MCP | Composio |
| --- | --- | --- | --- |
| Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Pendo (US1) tools | Allow or restrict single Pendo (US1) tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Pendo (US1) call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | $15 per user per month. | 2 tasks per successful call. | Billed per tool call. |

Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## Frequently asked questions

### How do I connect Pendo (US1) to Claude?

Two steps. In Elaichi, choose the Pendo (US1) connector and sign in to Pendo over OAuth, which is the ordinary Pendo login screen for the US1 region, with no OAuth application to register and no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Pendo in US1 appears in Claude the next time you open it.

### Does Pendo (US1) work with ChatGPT and Cursor as well as Claude?

Yes. Pendo in US1 is connected once in Elaichi, and the same endpoint, https://api.elaichi.ai/mcp, is pasted into Claude, ChatGPT, Cursor, any other MCP client, or used by the Elaichi Agent. There is nothing to set up separately for each client.

### What can an AI agent actually do with my Pendo (US1) data?

With Pendo in US1 connected, an agent can look up accounts and visitors, read their activity and usage over time, compare product areas and applications, report the product engagement score, and create, update or delete segments. In practice that means asking which accounts dropped off last month or asking for a segment of visitors who tried a feature once. Short, concrete asks work better than long paragraphs.

### Does connecting Pendo (US1) give the AI access to every account and visitor?

No. Access to Pendo in US1 follows the person who signed in, so the agent sees only the applications, accounts and visitors that person can already see in Pendo. Elaichi can narrow that further by role and restriction, and it can never widen it beyond what Pendo itself allows.

### Can my team share one Pendo (US1) connection?

Yes. One person connects Pendo in US1 and shares the connection with a team in Elaichi, and nobody else ever handles a credential. Each teammate still signs in to Elaichi as themselves, so every call to Pendo is logged under the name of the person who made it.

### Can I stop an agent from deleting or changing segments in Pendo (US1)?

Yes. Restrictions in Elaichi work per action, so you can allow reading accounts and usage from Pendo in US1 while blocking the actions that create, update or delete segments. A restricted action is never advertised to Claude, ChatGPT or Cursor at all, so no prompt can reach it.

### What happens to a Pendo (US1) connection when someone leaves?

Offboarding the person in Elaichi ends their access to Pendo in US1 at once, across every client they used. If they shared a Pendo connection with a team, it keeps working for everyone else. Disconnecting Pendo (US1) once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client together.

### Does the Pendo (US1) MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Pendo (US1) is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

### Is Elaichi an alternative to Zapier MCP for Pendo (US1)?

Yes. Both let Claude, ChatGPT or Cursor use Pendo (US1). Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Pendo (US1) call.

### How is Elaichi different from Composio for Pendo (US1)?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Pendo (US1): one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.

## All 87 Pendo (US1) tools

Every tool below is callable through https://api.elaichi.ai/mcp once Pendo (US1) is connected, subject to the toolbox it is in and the restrictions on the caller.

- **List all applications** (List). 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 aggregateEntityUsage for usage data). Also confirms which application data you have access to through authentication.
- **Search entities** (Search). Find Pendo items by name or conceptual meaning, including Pages, Features, Track Events, accounts, and saved clips. (Deprecated for guides and product areas).
- **Segment list** (List). List all publicly shared segments with their names and IDs.
- **Get entity** (Get). 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…
- **List custom objects** (List). List the custom event properties designated as business objects. Returns each object's underlying field and kind, customer-facing display name and description when configured, and the date it was promoted to an object.
- **Get segment** (Get). Retrieve the full definition and details for a single saved segment by ID.
- **Create segment** (Create). Create a new saved segment in Pendo.
- **Update segment** (Update). Update an existing saved segment's definition or name.
- **Delete segment** (Delete). Delete a saved segment by ID.
- **Account metadata schema** (Action). 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.
- **Visitor metadata schema** (Action). 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.
- **List accounts** (List). List or search accounts. You can list accounts matching an inline or saved segment, or search for accounts without providing an App ID.
- **List visitors** (List). List visitors matching an inline or saved segment.
- **Build pendo segment** (Action). 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.
- **Visitor activity** (Action). Return a chronological activity timeline for one visitor, with available developer console and network logs interleaved with product activity.
- **Product area member activity** (Action). Return all Pages, Features, and Track Events belonging to a product area, including those with zero activity in the date range.
- **List product areas** (List). List all product areas for a subscription, including their IDs, names, and descriptions. Supports optional fuzzy search and pagination.
- **List countables** (List). List or search Pages, Features, and Track Events. For Features, you can provide a Page ID to restrict results to Features associated with that Page.
- **Entity usage** (Action). Retrieve usage metrics for a single Page, Feature, or Track Event. Break results down by visitor or account, or group them by up to two event properties or metadata fields. Metadata can be the value recorded when the event happened, or the visitor's or account's current value.…
- **Entity usage time series** (Action). Retrieve usage metrics for a single Page, Feature, or Track Event, bucketed by day, week, or month. You can group or filter results by event properties or metadata, and sum a numeric event property, in the same way as entityUsage. The sum is returned for each bucket. Use the…
- **Aggregate entity usage** (Action). Rank all Pages, Features, or Track Events of a given type by usage.
- **App usage** (Action). Retrieve app-level usage metrics, broken down by visitor or account. Optionally return requested visitor or account metadata fields with each row.
- **App usage time series** (Action). Retrieve app-level usage metrics over time, bucketed by day, week, or month. Use the optional minEvents input to count only visitors who generated at least that many events within each bucket. The threshold is applied independently to every bucket and counts events, not visits.
- **Product engagement score** (Action). 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.
- **Query funnel** (Search). Calculate an ordered two- or three-step funnel for visitors or objects. Funnel steps can use Pages, Features, and Track Events.
- **Acquisition trend** (Action). Measure first-time visitors or accounts by period.
- **Cohort retention curve** (Action). 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…
- **Agent analytics key metrics** (Action). Retrieve key aggregate metrics for an AI agent's conversations, including prompt volume, visitor and account counts, rage prompt rates, and retention.
- **List AI agents** (List). 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 use cases** (List). Retrieve conversation clustering analysis for an AI agent, grouping prompts and conversations by semantic topic.
- **List AI agent issues** (List). Retrieve detected issues in AI agent conversations.
- **Agent analytics issue analysis** (Action). Retrieve issue diagnoses, flagged response tool and model usage, and visitor prompt content for the events of a specific detected issue cluster.
- **Agent analytics use case analysis** (Action). Perform a detailed analysis of one emergent (automatically clustered) use case identified by listUseCases.
- **List tracked issues** (List). List user-defined tracked issues for an AI agent.
- **List tracked use cases** (List). List user-defined tracked use cases for an AI agent.
- **Agent analytics conversation analysis** (Action). Perform a detailed analysis of selected AI agent conversations.
- **Agent analytics tracked issue analysis** (Action). Perform a detailed analysis of one tracked issue, including sampled visitor prompts and tool or model usage.
- **Agent analytics tracked use case analysis** (Action). Perform a detailed analysis of one tracked use case.
- **Command center apps** (Action). 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…
- **Update command center app** (Update). Update an app's license count, annual cost, renewal date, or notes (individually or several at once) for a single managed or discovered app.
- **Object analytics time series** (Action). Track engagement with a business object over time, grouped into daily, weekly, or monthly buckets. By default, engagement is measured as average time per object.
- **List guides** (List). List, filter, and optionally retrieve full content for in-app guides, including IDs, names, states, types, and scheduling.
- **Guide poll responses** (Action). Analyze poll responses collected in a guide.
- **Guide effectiveness metrics** (Action). Return dashboard-consistent guide engagement, completion, and goal-adoption rates, with filtering and segment comparison.
- **Aggregate guide metrics** (Action). 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.
- **Guide usage** (Action). Break down usage of a single guide by visitor or account, or inspect each guide step's visitor count and time on step.
- **List guide categories** (List). Return the guide-category tree for a subscription.
- **List guide ordering** (List). Return guide display-order rules for an application.
- **Guide set state** (Set). Change the state of a guide, such as publishing a draft, staging a guide for review, or making an active guide inactive.
- **Guide set segment** (Set). Update the audience segment targeting for a guide.
- ...and 37 more tools. Call `tools/list` via the MCP endpoint, or see the full catalog via the API, for the complete set.