Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the CodeRabbit 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%2Fcoderabbit.ai%2Fcoderabbit" | 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%2Fcoderabbit.ai%2Fcoderabbit" | 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 CodeRabbit API.
Generate an on-demand code-review report for a date range
Read pull-request review metrics
List users in the CodeRabbit organization
Allocate and manage review seats
Get and set the seat-assignment mode
Assign roles to users
Patterns agents use CodeRabbit API for, with concrete tasks.
★ Engineering review reporting
Engineering leads want a regular summary of code-review activity. The CodeRabbit API generates a report for a date range and exposes review metrics, so a reporting job can produce weekly review statistics without manual collection.
Generate a review report for the past week and read the review metrics for a summary
Seat and license administration
Teams managing CodeRabbit licenses need to assign and reclaim seats as developers join and leave. The API lists users, manages seat allocations, and sets the seat-assignment mode so onboarding can be automated.
List users, assign a seat to a new developer, and set the seat-assignment mode to automatic
Agent-driven review operations
A developer-experience agent can keep review tooling tidy on request. Through Jentic, an agent resolves a request like preparing a new hire into listing users, assigning a seat, and setting the right role.
Onboard a developer by assigning a review seat and granting the appropriate role
7 endpoints — coderabbit is an ai code-review platform, and this api covers the account-management surface around it.
METHOD
PATH
DESCRIPTION
/api/v1/report.generate
Generate a code-review report
/v1/metrics/reviews
Get pull-request review metrics
/v1/users
List users
/v1/users/seats
Manage review seats
/v1/users/roles
Assign user roles
/api/v1/report.generate
What agents get from Jentic-routed access to this vendor.
Setup
CodeRabbit wiring is one API key plus seven admin operations. With Jentic One you install once, import them from the API Directory, and keep the key in a single place.
Permission scoping
Operations act on org-level resources rather than per-repository ids, so scoping is at the operation level: an agent can be limited to reading metrics while seat and role writes are withheld.
Credential isolation
Your CodeRabbit API key is stored encrypted by your own Jentic One instance and injected when a call runs, so it never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents find the right CodeRabbit operation through Jentic's intent search, matching a request like generating a code-review report to the matching endpoint.
Alternatives and complements available in the Jentic catalogue.
Specific to using CodeRabbit API through Jentic.
How does the CodeRabbit API authenticate?
CodeRabbit authenticates with an API key sent in the `x-coderabbitai-api-key` header, as declared in its OpenAPI spec. Jentic One stores that key and injects it at execution time.
Can I limit what my agent is allowed to do in CodeRabbit?
Yes. You import only the operations an agent needs, so a reporting agent can read metrics and generate reports while seat and role changes stay out of scope.
Does this API run the code reviews itself?
No. The automated reviews run in CodeRabbit's connected source-control app; this API covers reporting and account administration around them.
What does the report generation operation return?
It produces an on-demand code-review report for the date range you request, which you can read back as structured data for dashboards or summaries.
Can I manage CodeRabbit seats and roles through the API?
Yes. The API lists users, allocates seats, sets the seat-assignment mode, and assigns roles, so license administration can be automated.
GET STARTED
Generate a code-review report
/v1/metrics/reviews
Get pull-request review metrics
/v1/users
List users
/v1/users/seats
Manage review seats
/v1/users/roles
Assign user roles
For Agents
Lets an AI agent generate CodeRabbit review reports and manage users, seats, and roles with an API key.
Use for: I want a CodeRabbit review report for last week, Show me our pull-request review metrics, List everyone using CodeRabbit in our org, Assign a review seat to a new developer
Not supported: Does not configure review rules or run the reviews itself: use it for CodeRabbit reporting and user, seat, and role administration only.
CodeRabbit is an AI code-review platform, and this API covers the account-management surface around it. With an API key, an integration can generate on-demand review reports for a date range, read pull-request review metrics, list users, manage seat allocations and the seat-assignment mode, and set user roles. It is the administrative companion to CodeRabbit's automated pull-request reviews.
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>