Roborabbit API
Official vendor OpenAPI document · agent-readyData EnrichmentData Transformationbearer8 EndpointsREST
For Agents
Run configured browser automation tasks that navigate websites and return structured data. List and inspect tasks, start runs, read run results, and pull feeds of collected data.
Use for: Run a browser automation task, List the configured tasks, Start a task run and get its result, Read the results of a past run
Not supported: Does not handle proxy management, CAPTCHA solving, or data warehousing. Use for running browser automation tasks and reading their results only.
The Roborabbit API runs browser automation tasks that navigate websites and return structured data. It lists and inspects configured tasks, starts a run, reads the results of past runs, and pulls feeds of collected data, so an agent can extract web data without operating a browser itself.
Install Jentic One Beta
Connect the Roborabbit API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Roborabbit 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.
1
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%2Fapi.roborabbit.com%2Froborabbit" | sh2
Step 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%2Fapi.roborabbit.com%2Froborabbit" | 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.
Capabilities
What an agent can do with Roborabbit API.
List the browser automation tasks configured in a workspace
Inspect a single task and its configuration
Start a run of a task to collect data from the web
List and read the results of a task's past runs
Pull feeds of data collected by tasks
Check the authenticated account for the token
Use Cases
Patterns agents use Roborabbit API for, with concrete tasks.
★ Web Data Extraction Agent
An AI agent collects data from a website by starting a Roborabbit task run, waiting for it to finish, and reading the structured result. Through Jentic the agent discovers the task and run operations by intent and calls them directly, so it gathers web data without driving a browser or maintaining scraping code.
Start a task run against a target site and return the structured data it collects
Scheduled Data Feeds
Pull feeds of data that Roborabbit tasks have already collected, so an agent can consume fresh results without triggering a new run each time. This keeps a downstream dataset current from tasks that run on their own schedule.
Pull the latest feed and load new records into a downstream store
Run Result Retrieval
Read the results of past task runs to reconcile or reprocess collected data. The agent lists a task's runs, fetches a specific run, and works from the exact result it produced, without re-running the automation.
List a task's recent runs and fetch the result of the most recent one
Key Endpoints
8 endpoints — the roborabbit api runs browser automation tasks that navigate websites and return structured data.
METHOD
PATH
DESCRIPTION
GET
/v1/tasks
List browser automation tasks
GET
/v1/tasks/{uid}
Get a task's details
POST
/v1/tasks/{task_uid}/runs
Start a task run
GET
/v1/tasks/{task_uid}/runs
List a task's runs
GET
/v1/feeds
Pull feeds of collected data
GET
/v1/tasks
List browser automation tasks
GET
/v1/tasks/{uid}
Get a task's details
POST
/v1/tasks/{task_uid}/runs
Start a task run
GET
/v1/tasks/{task_uid}/runs
List a task's runs
GET
/v1/feeds
Pull feeds of collected data
Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Roborabbit API by hand means handling its bearer-token auth and the start-run then poll-result sequence yourself. Through Jentic you install once, import Roborabbit from the API Directory, store the token once, and your agent calls it.
Permission scoping
Roborabbit identifies tasks and runs by an id in the request path, so a rule bounds which operations your agent may call. You choose those operations, so it can start runs and read results while task configuration stays out of scope unless you add it.
Credential isolation
Your Roborabbit token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'run a browser automation task' or 'read a run result', and Jentic returns the matching Roborabbit operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Roborabbit API through Jentic.
What authentication does the Roborabbit API use?
The Roborabbit API authenticates with a bearer token, your workspace API key, in the Authorization header, per its OpenAPI spec. Through Jentic the token is stored encrypted by your own Jentic One instance and injected at call time, so it never enters the agent's prompt or logs.
Can I run a browser automation task with the Roborabbit API?
Yes. Call POST /v1/tasks/{task_uid}/runs to start a run of a configured task, then GET /v1/tasks/{task_uid}/runs/{uid} to read its result once it completes. GET /v1/tasks lists the tasks you can run.
What are the rate limits for the Roborabbit API?
The OpenAPI spec does not specify rate limits. Check the Roborabbit documentation at https://developers.roborabbit.com before starting many runs in parallel.
Is there a Roborabbit MCP server?
You don't need an MCP server to give your agent the Roborabbit API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls the task and run operations it needs.
Can I limit what my agent is allowed to do with the Roborabbit API?
Yes. Write a rule that allows only starting runs and reading results, so the agent can collect data while task configuration and account operations stay out of scope, and every call it makes is logged.
How do I run a task with the Roborabbit API through Jentic?
Search Jentic for 'run a browser automation task', and it returns the POST /v1/tasks/{task_uid}/runs and result operations with their input schemas so your agent collects the data directly. To run it on your own infrastructure, install Jentic One from its GitHub repo.
GET STARTED