Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Webull OpenAPI, 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%2Fwebull.com%2Fwebull" | 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%2Fwebull.com%2Fwebull" | 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 Webull OpenAPI API.
Get account list
Place an order
Cancel an order
Replace/modify an order
Monitor Webull OpenAPI operational status and events
GET STARTED
Patterns agents use Webull OpenAPI API for, with concrete tasks.
★ CRM Operations
Use the Webull OpenAPI to perform crm operations programmatically. The API provides 13 endpoints covering core functionality including get account list, get account balance, get account positions.
Call GET /openapi/account/list to get account list
Automated Accounts Management
Automate accounts operations by combining multiple Webull OpenAPI endpoints. Agents can get account balance and then get account positions in a single workflow.
Call GET /openapi/assets/balance to get account balance, then verify the result
AI Agent Integration via Jentic
AI agents discover and call Webull OpenAPI endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle apiKey tokens manually.
Search Jentic for 'get account list', load the operation schema, and execute with Jentic-managed credentials
13 endpoints — webull openapi provides programmatic access to trading, account management, and market data on the webull platform.
METHOD
PATH
DESCRIPTION
/openapi/account/list
Get account list
/openapi/assets/balance
Get account balance
/openapi/assets/positions
Get account positions
/openapi/trade/order/place
Place an order
/openapi/trade/order/cancel
Cancel an order
/openapi/trade/order/replace
Replace/modify an order
/openapi/trade/order/list
Get order list
/openapi/trade/order/detail
Get order detail
/openapi/account/list
Get account list
/openapi/assets/balance
Get account balance
/openapi/assets/positions
Get account positions
/openapi/trade/order/place
Place an order
/openapi/trade/order/cancel
Cancel an order
/openapi/trade/order/replace
Replace/modify an order
/openapi/trade/order/list
Get order list
/openapi/trade/order/detail
Get order detail
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Webull OpenAPI by hand means sending both its app_key and a computed sign header on every request and handling retries yourself. Through Jentic you install once, import Webull OpenAPI from the API Directory, store the keys once, and your agent calls it.
Permission scoping
Webull carries account and order details in the request body rather than in the path, so limit the agent to the operations it needs, such as listing accounts or reading balances and positions. You choose the operations it may call, so trade actions like placing, cancelling, or replacing an order are not included unless you add them.
Credential isolation
Your Webull app key and signing key are stored once, encrypted, by your own Jentic One instance 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 'list my accounts' or 'get my positions', and Jentic returns the matching Webull 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 Webull OpenAPI API through Jentic.
What authentication does the Webull OpenAPI use?
The Webull OpenAPI uses an API key passed in the `app_key` header. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.
Can I get account list with the Webull OpenAPI?
Yes. Use the GET /openapi/account/list endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the Webull OpenAPI?
Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.
How do I get account list through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'get account list'. Jentic returns the matching Webull OpenAPI operation with its input schema. Load the schema and execute the call - credentials are injected automatically.
How many endpoints does the Webull OpenAPI have?
The Webull OpenAPI exposes 13 endpoints covering accounts, market data, trading operations.
Can I limit what my agent is allowed to do with the Webull OpenAPI?
Yes. Because you run Jentic One yourself, you decide which Webull operations the agent can call, so you can grant read-only access to GET /openapi/account/list, GET /openapi/assets/balance, and GET /openapi/assets/positions while withholding everything else. Webull carries account and order details in the request body rather than the path, so trade actions such as POST /openapi/trade/order/place, /cancel, and /replace stay unavailable unless you deliberately add them. Your app key and signing key are stored encrypted by your own instance and injected only for the operations you allow, so the agent never sees raw secrets or reaches endpoints outside its scope.
For Agents
Programmatically get account list, get account balance. Covers 13 operations with apiKey authentication.
Use for: I need to account list, I want to account balance, Search for account positions, Find all place an order
Not supported: Does not handle payments, communications, or developer tools - use for crm only.
Webull OpenAPI provides programmatic access to trading, account management, and market data on the Webull platform. Supports stock, options, futures, and crypto trading. Authentication uses app_key and app_secret with HMAC signing. The API exposes 13 endpoints secured with apiKey authentication.
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>