Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Pendo Feedback API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fpendo.io%2Fpendo" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fpendo.io%2Fpendo" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Pendo Feedback API.
Read accounts and the users who submit feedback
List requested features and the votes cast for them
Record a vote on a feature on a user's behalf
Read the comments users leave on feature requests
Tag accounts, users, and features to segment them
GET STARTED
Search across feedback data and invite users
Register and remove webhooks for feedback events
Patterns agents use Pendo Feedback API for, with concrete tasks.
★ Sync demand signals into planning tools
Bring feature requests and their vote counts into the tools a product team already plans with. The agent reads the requested features and the votes cast for them so a roadmap or ticketing system can rank work by real user demand instead of guesswork.
Read the requested features and their votes and return them ranked by vote count for a planning tool.
Record feedback captured elsewhere
Feed feedback gathered outside Pendo Feedback back into it. The agent records a vote on a feature on a user's behalf so a support conversation or sales call that surfaced a request is reflected alongside in-product feedback.
Record a vote on the named feature for the given user so external feedback joins the in-product signal.
Segment feedback with tags
Group feedback by the attributes a team cares about. The agent tags accounts, users, and features so demand can be sliced by segment, such as plan tier or region, when the data is analysed.
Apply the requested tags to the given accounts, users, or features so feedback can be segmented.
React to feedback in real time
Trigger workflows when feedback changes. The agent registers a webhook so a downstream system is notified as new votes or requests arrive, and removes the subscription when it is no longer needed.
Register a webhook for feedback events, or unsubscribe an existing one when it is no longer needed.
31 endpoints — pendo feedback api manages the product-feedback loop that pendo feedback captures from users.
METHOD
PATH
DESCRIPTION
/accounts
List the accounts submitting feedback
/features
List the requested features
/votes
List the votes cast on features
/votes
Record a vote on a feature
/users/{id}
Read a single user by identifier
/accounts
List the accounts submitting feedback
/features
List the requested features
/votes
List the votes cast on features
/votes
Record a vote on a feature
/users/{id}
Read a single user by identifier
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Pendo Feedback API by hand means provisioning the auth-token key, learning how accounts, features, votes, and comments relate, and handling tags and webhooks. Through Jentic you install once, import Pendo Feedback from the Jentic API Directory, configure the key, and your agent calls it.
Permission scoping
Feedback data spans reads and writes across many resources, and because Jentic One is self-hosted, your own rules decide which the agent may call. You can allow reading features and votes while withholding operations that delete accounts or users, so the agent reaches only what you approved.
Credential isolation
Your Pendo Feedback auth-token key is held encrypted by your own Jentic One instance and attached to requests only at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent, such as listing feature votes or recording a vote, and Jentic returns the matching Pendo Feedback operation with typed inputs, so the agent calls the right one without scanning all 31 operations.
Alternatives and complements available in the Jentic catalogue.
Specific to using Pendo Feedback API through Jentic.
What authentication does Pendo Feedback API use?
Pendo Feedback API authenticates with an API key named auth-token, which you send as a request header or as a query parameter. Through Jentic, the key you configure is held encrypted by your own Jentic One instance and attached to requests at execution time. Check Pendo's developer documentation for how to obtain the key.
Can I write feedback back into Pendo Feedback, or only read it?
You can do both. Alongside reading accounts, features, votes, and comments, the API lets you record a vote on a feature, tag records, and invite users, so feedback gathered elsewhere can be reflected in Pendo Feedback.
What are the rate limits for Pendo Feedback API?
The OpenAPI description does not specify rate limits. Check Pendo's developer documentation for the limits on your account before syncing feedback in bulk.
Is there an MCP server for Pendo Feedback?
You don't need an MCP server to use Pendo Feedback with your agent. Through Jentic, your agent finds the feedback operations by intent and calls them directly, with your credentials injected at run time by your own Jentic One instance.
How do I connect Pendo Feedback API to my agent through Jentic?
To run it on your own infrastructure, install Jentic One from its GitHub repo, then import Pendo Feedback API from the Jentic API Directory and configure your auth-token key. Your agent can then read and update feedback with that key injected at execution time.
Can I limit what my agent is allowed to do with Pendo Feedback API?
Yes. Because Jentic One is self-hosted, your own rules decide which Pendo Feedback operations the agent may call, so you can allow reading features and votes while withholding operations that delete accounts or users. Your key stays encrypted on your own instance and is attached only when a permitted request runs.
Know of an official OpenAPI document? Contribute it →
For Agents
Work with product feedback in Pendo Feedback: read accounts, users, features, votes, and comments, tag records, and register webhooks for feedback events.
Use for: List the accounts sending us feedback, Show the features users are requesting, Read the votes on a feature, Record a vote for a feature on behalf of a user
Not supported: Manages product feedback: accounts, users, features, votes, comments, tags, and webhooks. Does not track in-app product usage analytics or run in-app guides, which are separate Pendo products.
Pendo Feedback API manages the product-feedback loop that Pendo Feedback captures from users. It exposes the accounts and users the feedback comes from, the features being requested, the votes users cast for those features, and the comments they leave. You can tag accounts, users, and features to segment them, search across the data, and register webhooks so your systems react when feedback changes. It fits product and customer-success teams that want feedback and demand signals flowing into their own tools rather than staying inside a dashboard.