Pendo MCP connector for AI agents

Tools your analytics agent reaches for on Pendo MCP, scoped per user.

CALL ANY TOOL

The Pendo MCP tool set gives agents access to product analytics data — from querying visitor behavior and account metadata to listing segments, searching product entities, and computing engagement scores.

pendomcp_accountmetadataschema

Accountmetadataschema

Return the set of metadata fields available for accounts.

Parameters

Name

Type

Required

Description

subId

string

Required

Subscription ID that owns the data. Required for all queries.

userQuery

string

Optional

The original user query or question that triggered this tool call.

pendomcp_accountquery

Accountquery

pendomcp_activityquery

Activityquery

Query aggregated activity metrics for pages, features, and track types over a date range.

Parameters

Name

Type

Required

Description

appId

string

Required

Application id of the app to query

dateRange

object

Required

The time period to query. Use 'relative' with lastNDays or 'custom' with explicit dates.

entityType

string

Required

The entity type to query

subId

string

Required

Subscription ID that owns the data. Required for all queries.

accountId

string

Optional

Filter results to a specific account. REQUIRED when the user mentions or references a specific account. Use the exact account ID string

count

boolean

Optional

Set to true to return only the total count of matching records instead of rows.

featureFlag

object

Optional

Filter events to those where a feature flag was set. Object: {name, value}. e.g. {"name": "myFlag", "value": true}. Use value:false to filter to events where the flag is not true.

frustrationMetrics

boolean

Optional

Toggles return of frustration metrics: error click/rage click/u-turn/dead click count

group

array

Optional

Fields to group results by. e.g. ["featureId"] for per-feature rows, ["visitorId"] for per-visitor rows. Any field in select can be used.

historicalMetadataFilter

object

Optional

Filter by metadata values at event time (not current). Object: {kind, group, field, op, value}. kind: visitor|account|parentAccount. op: == != < > <= >=. e.g. {"kind":"visitor","group":"agent","field":"email","op":"==","value":"\"user@example.com\""}

itemIds

array

Optional

The item ids to query

limit

number

Optional

Maximum number of rows to return. Range: 1-1000. Default: 1000.

period

string

Optional

Aggregation period: dayRange (default), day, week, month. Controls how date ranges are bucketed in results.

productAreaId

string

Optional

Scope query to one product area. Mutually exclusive with itemIds. Use listProductAreas to find the ID.

segmentId

string

Optional

filter the results by the specified segment id. If not provided, no segment filtering is applied.

sort

array

Optional

The fields to sort by. Prepending the field with a + (ascending) or - (descending) determines the sort direction.

userQuery

string

Optional

The original user query or question that triggered this tool call.

visitorId

string

Optional

Filter results to a specific visitor. REQUIRED when the user mentions or references a specific visitor. Use the exact visitor ID string

visitorMetadataFilter

string

Optional

Filter activity by visitor metadata (current values). e.g. metadata.auto.country == "US" && metadata.custom.plan == "enterprise". Mutually exclusive with segmentId.

pendomcp_agent_analytics_key_metrics

Agent Analytics Key Metrics

pendomcp_ai_agent_issue_analysis

Ai Agent Issue Analysis

pendomcp_get_agent_context

Get Agent Context

pendomcp_guidemetrics

Guidemetrics

pendomcp_list_ai_agent_issues

List Ai Agent Issues

pendomcp_list_ai_agents

List Ai Agents

pendomcp_list_all_applications

List All Applications

pendomcp_list_spaces

List Spaces

pendomcp_list_use_cases

List Use Cases

pendomcp_listguides

Listguides

pendomcp_listproductareas

Listproductareas

pendomcp_productareamemberactivity

Productareamemberactivity

pendomcp_productengagementscore

Productengagementscore

Calculate the Product Engagement Score for an application over a date range, returning adoption, stickiness, and growth metrics.

Parameters

Name

Type

Required

Description

appId

string

Required

Application id of the app to query

endDate

string

Required

Query end date in YYYY-MM-DD format (e.g., '2025-01-31'). Inclusive.

startDate

string

Required

Query start date in YYYY-MM-DD format (e.g., '2025-01-01'). Inclusive.

subId

string

Required

Subscription ID that owns the data. Required for all queries.

accountId

string

Optional

Filter results to a specific account. REQUIRED when the user mentions or references a specific account. Use the exact account ID string

adoptionUserBase

string

Optional

The user base for the adoption score.

blacklist

string

Optional

Blacklist behavior: 'apply' (use blacklist, normal behavior), 'ignore' (do not use blacklist), 'only' (invert blacklist, return only blacklisted activity)

excludeWeekends

boolean

Optional

Whether to exclude weekends in the stickiness score calculation.

featureIds

array

Optional

Array of the featureIds to include in the adoption score calculation. If this, pageIds, and trackEventIds are empty, default core events are included.

growthUserBase

string

Optional

The user base for the growth score.

pageIds

array

Optional

Array of the pageIds to include in the adoption score calculation. If this, featureIds, and trackEventIds are empty, default core events are included.

scores

array

Optional

Array of the scores to return. If empty, only PES is returned

segmentId

string

Optional

filter the results by the specified segment id. If not provided, no segment filtering is applied.

stickinessDenominator

string

Optional

The denominator time range for the stickiness score. If denominator is provided, numerator must also be provided. Numerator cannot equal denominator.

stickinessNumerator

string

Optional

The numerator time range for the stickiness score. If numerator is provided, denominator must also be provided. Numerator cannot equal denominator.

stickinessUserBase

string

Optional

The user base for the stickiness score.

trackEventIds

array

Optional

Array of the trackEventIds to include in the adoption score calculation. If this, pageIds, and featureIds are empty, default core events are included.

userQuery

string

Optional

The original user query or question that triggered this tool call.

pendomcp_searchentities

Searchentities

pendomcp_segmentlist

Segmentlist

pendomcp_visitormetadataschema

Visitormetadataschema

pendomcp_visitorquery

Visitorquery

Build your Agent

Same auth pattern across every framework.

from langchain_mcp_adapters.client import MultiServerMCPClient
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="pendomcp")

mcp = MultiServerMCPClient({
    "pendomcp": {
        "url": "https://mcp.scalekit.com/pendomcp",
        "headers": {"Authorization": "Bearer " + token}
    }
})
tools = await mcp.get_tools()

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "pendomcp" });

const openai = new OpenAI();
// Connect to MCP at https://mcp.scalekit.com/pendomcp
// Pass: Authorization: Bearer + token

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "pendomcp" });

const anthropic = new Anthropic();
// Connect to MCP at https://mcp.scalekit.com/pendomcp
// Pass: Authorization: Bearer + token

from google.adk.agents import LlmAgent
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="pendomcp")
# Connect to MCP at https://mcp.scalekit.com/pendomcp
# Pass: Authorization: Bearer + token

Try these prompts

Paste any prompt into your agent to get started.

Analyze & explore data

Copy the prompt

Copied

Show me the Product Engagement Score for our main application over the last 90 days, broken down by adoption, stickiness, and growth.

Copy the prompt

Copied

List all segments in our Pendo subscription and tell me which ones have feature flags associated with them.

Investigate user behavior

Copy the prompt

Copied

Search for all guides related to onboarding in our application and show me which product areas they belong to.

Copy the prompt

Copied

Get all pages and features in our 'Core Workflow' product area, including any with zero activity, so I can identify unused parts of the product.

SEE HOW AUTH WORKS

User authorises once. Every agent call after uses their token with scope enforcement.

Authorize

Your user connects

Pendo MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Pendo MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Pendo MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Pendo MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other connectors.

SALES

Deal intelligence agent

Combine Gong, Attio, and Slack signals to surface deal risks and next-best actions. Updated after every call.

ENGINEERING

Engineering standup agent

Aggregate GitHub and GitLab activity, link to Jira, and post a daily standup digest to Slack. No async updates.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential.

// shared token
 audit → bot_service_account

 // scalekit
 audit → user_abc ✓

02.

Authentication is not authorization

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Pendo MCP as the user or as a shared key?

Scalekit resolves a per-user credential for each call. The Pendo MCP audit log shows the real user identity, not a shared service account.

Where is the Pendo MCP token stored?

In Scalekit's AES-256 encrypted vault, isolated per tenant. Tokens are auto-refreshed before expiry and revocable from a single dashboard without code changes.

Can I limit what the agent is allowed to do in Pendo MCP?

Pass a toolNames filter to listScopedTools. Scalekit enforces the allowed set before every API call — the agent cannot invoke tools outside the approved list.

What happens when a user revokes Pendo MCP access?

The token is invalidated at the next tool call. The agent fails closed rather than falling back to a shared key. Other users are unaffected and the revocation event is logged with a timestamp.

Pendo's API has rate limits per subscription. How does Scalekit prevent one agent from exhausting quota for all users?

Scalekit resolves credentials per user, so each agent call runs under that user's own Pendo API context. Rate limit consumption is attributed to the individual token rather than a single shared key, distributing quota across users and preventing one agent from blocking others.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit