Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Phyllo Creator Economy 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%2Fgetphyllo.com%2Fphyllo" | 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%2Fgetphyllo.com%2Fphyllo" | 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 Phyllo Creator Economy API.
Create a user and issue an SDK token so a creator can link their platform accounts
Read connected account status and update its monitoring settings
Retrieve creator profiles and audience demographics across linked work platforms
List published content, content groups, and comments for a connected creator
GET STARTED
Pull social and commerce income transactions and payouts for a creator
Register webhooks to receive updates when creator data refreshes
Patterns agents use Phyllo Creator Economy API for, with concrete tasks.
★ Agent-Driven Creator Onboarding
An AI agent connected through Jentic onboards a creator by creating a Phyllo user, issuing an SDK token for account linking, and then reading back the connected accounts and profile once the creator authorizes. Because Phyllo normalizes data across YouTube, Instagram, TikTok, and other work platforms, the agent handles one schema instead of a different integration per platform.
Create a Phyllo user, generate an SDK token, then list the connected accounts and retrieve the creator profile
Influencer Audience and Engagement Analysis
Marketing tools analyzing an influencer pull audience demographics, published content, and comments for a connected account. Phyllo returns audience breakdowns and content items filtered by account, so an agent assembles a creator's reach and engagement picture without scraping each platform directly.
Retrieve audience demographics and the latest content items for a connected account and summarize engagement
Creator Income Reconciliation
Platforms paying creators reconcile earnings by pulling social income transactions and payouts alongside commerce income transactions. Phyllo separates social and commerce income and exposes individual transactions and payouts, so a finance agent reconciles what a creator earned against what was paid out.
Retrieve social income transactions and payouts for a creator and match each payout to its transactions
33 endpoints — the phyllo creator economy api retrieves a connected creator's identity, audience demographics, published content, comments, and income across social and commerce platforms through one unified interface.
METHOD
PATH
DESCRIPTION
/v1/users
Create a user to represent a creator
/v1/sdk-tokens
Issue an SDK token for account linking
/v1/accounts
List connected creator accounts
/v1/profiles
Retrieve creator profiles
/v1/audience
Retrieve audience demographics
/v1/social/income/transactions
Retrieve social income transactions
/v1/users
Create a user to represent a creator
/v1/sdk-tokens
Issue an SDK token for account linking
/v1/accounts
List connected creator accounts
/v1/profiles
Retrieve creator profiles
/v1/audience
Retrieve audience demographics
/v1/social/income/transactions
Retrieve social income transactions
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Phyllo by hand means handling its basic auth with a CLIENT_ID and CLIENT_SECRET, running the SDK-token flow so creators link accounts, and tracking refresh webhooks yourself. Through Jentic you install once, import Phyllo from the API Directory, store the credentials once, and your agent calls the creator-data operations.
Permission scoping
Phyllo carries read operations for profiles, audience, content, and income alongside write operations that create users, update account monitoring, and manage webhooks. You choose the operations your agent may call, so a rule can keep it to the read operations and leave user creation or webhook deletion out unless you add them.
Credential isolation
Your Phyllo CLIENT_ID and CLIENT_SECRET are held by your own Jentic One instance, encrypted, and injected at execution time. They never enter the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'retrieve creator audience demographics' or 'pull social income payouts', and Jentic returns the matching Phyllo operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Phyllo Creator Economy API through Jentic.
What authentication does the Phyllo Creator Economy API use?
The API uses HTTP basic authentication, sending your CLIENT_ID as the username and CLIENT_SECRET as the password, per its OpenAPI spec. Through Jentic those credentials are held by your own Jentic One instance and attached to each request at execution time, so they never appear in your agent's prompt or logs.
Can I retrieve creator income data with the Phyllo Creator Economy API?
Yes. Phyllo exposes social income transactions and payouts and separate commerce income transactions for a connected creator. Your agent lists transactions and payouts and reads individual records by id, so it can reconcile what a creator earned against what was paid out.
What are the rate limits for the Phyllo Creator Economy API?
The OpenAPI spec does not specify rate limits. Check the Phyllo documentation at https://docs.getphyllo.com/ for current limits before running high-volume data pulls.
Is there a Phyllo MCP server?
You do not need an MCP server to give your agent the Phyllo Creator Economy API. Jentic connects it directly from the API Directory: import it, store your credentials once, and your agent calls the creator-data operations on demand without loading an extra server's tool definitions into its context.
Can I limit what my agent is allowed to do with the Phyllo Creator Economy API?
Yes. Write a rule that allows only the read operations your agent needs, such as retrieving profiles, audience, and income, so it cannot create users, update account monitoring, or delete webhooks. You choose the operations it may call, and every call it makes is logged.
How do I pull creator data through Jentic?
Install the Jentic One command line with `curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh`, then add the Phyllo Creator Economy API from the Jentic directory and search by intent such as 'retrieve creator audience demographics'. Jentic returns the matching operation with its input schema so your agent builds a valid request. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Retrieve a creator's linked social and commerce accounts, profile and audience data, published content, and income transactions and payouts through Phyllo's unified creator-data API.
Use for: I need to create a Phyllo user and generate an SDK token for account linking, Retrieve the audience demographics for a connected creator, List all content items published by a linked creator account, Get the social income transactions for a creator over a date range
Not supported: Does not post content, run ad campaigns, or send creator payments. Use for retrieving connected creators' social and commerce data only.
The Phyllo Creator Economy API retrieves a connected creator's identity, audience demographics, published content, comments, and income across social and commerce platforms through one unified interface. Your app creates a user, issues an SDK token so the creator links their accounts, and then reads normalized profile, engagement, and payout data back from each linked work platform. Income is split into social and commerce transactions and payouts, and webhooks notify your systems when fresh data arrives.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>