Install Jentic One Beta

Connect the Prisma Postgres Management API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Prisma Postgres Management 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%2Fprisma.io%2Fprisma" | sh

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%2Fprisma.io%2Fprisma" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic 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 Prisma Postgres Management API.

Create a project with a Prisma Postgres database in a chosen region, or add a database to an existing project

Issue a named connection string for a database and rotate a connection's credentials

List a database's backups and restore a target database from a backup source

Read database usage metrics between a startDate and endDate

GET STARTED

Start building with Prisma Postgres Management API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Prisma Postgres Management API for, with concrete tasks.

★ Agent-provisioned Postgres for new projects

A coding agent scaffolding an app can create the database it needs instead of asking you to click through a console. Through Jentic the agent searches for 'create a Postgres database', reads the available regions from getV1RegionsPostgres, calls postV1Projects with a name and region to create a project with a database, and then creates a named connection string to write into the app's environment.

GET /v1/regions/postgres, POST /v1/projects with name 'todo-app' and a region from the list, then POST /v1/databases/{databaseId}/connections with name 'local-dev'

Preview databases per git branch

Teams that open a preview environment per pull request can create a Prisma branch keyed by the git branch name, then add a database tied to that branchId. When the pull request closes, the branch is soft-deleted. The branch endpoints are marked experimental in the spec, so callers should expect changes.

POST /v1/projects/{projectId}/branches with gitName 'feature/login', then POST /v1/databases with projectId and the returned branchId

Backup checks and restores

Before a risky migration, an operator can list a database's backups to confirm a recent one exists. If the migration goes wrong, the restore operation overwrites the target database from the chosen backup source while keeping connections and credentials. The spec flags restore as destructive and irreversible, so it should only run with explicit approval.

GET /v1/databases/{databaseId}/backups and report the most recent backup, without calling the restore operation

Credential rotation and usage review

Routine hygiene work for a Prisma Postgres workspace includes rotating connection credentials and checking consumption. postV1ConnectionsByIdRotate generates new credentials for a connection, with revocation of the old ones handled best-effort, and the usage operation returns metrics for a database over a date range for cost review.

GET /v1/databases/{databaseId}/usage with startDate '2026-10-01' and endDate '2026-10-31', then POST /v1/connections/{id}/rotate for the app's connection

Key Endpoints

117 endpoints — the prisma postgres management api provisions and operates prisma postgres projects, databases, connections, and backups across your workspaces.

METHOD

PATH

DESCRIPTION

POST

/v1/projects

Create a project with a Postgres database

POST

/v1/databases

Create a database

POST

/v1/databases/{databaseId}/connections

Create a connection string

POST

/v1/connections/{id}/rotate

Rotate connection credentials

GET

/v1/databases/{databaseId}/backups

List database backups

GET

/v1/databases/{databaseId}/usage

Get database usage metrics

POST

/v1/projects/{projectId}/branches

Create a branch

GET

/v1/regions/postgres

List Prisma Postgres regions

POST

/v1/projects

Create a project with a Postgres database

POST

/v1/databases

Create a database

POST

/v1/databases/{databaseId}/connections

Create a connection string

POST

/v1/connections/{id}/rotate

Rotate connection credentials

GET

/v1/databases/{databaseId}/backups

List database backups

GET

/v1/databases/{databaseId}/usage

Get database usage metrics

POST

/v1/projects/{projectId}/branches

Create a branch

GET

/v1/regions/postgres

List Prisma Postgres regions

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring Prisma Postgres by hand means running the OAuth2 authorization code flow at auth.prisma.io or minting a workspace service token, refreshing tokens, and paging cursor-based lists across projects, databases, and branches. Through Jentic you install once, import Prisma Postgres from the API Directory, store the token once, and your agent calls it.

Permission scoping

Prisma puts the database, project, and branch ids in the URL path (/v1/databases/{databaseId}/..., /v1/projects/{projectId}/branches), so a rule can pin your agent to one database. You choose the operations it may call, so destructive ones like the backup restore, database deletion, or project deletion are not included unless you add them.

Credential isolation

Your Prisma token is stored once, encrypted, by your own Jentic One instance and injected into the Authorization header at execution time. It never enters the agent's prompt, logs, or context.

Intent-based discovery

Agents search Jentic by intent such as 'create a Postgres database' or 'rotate connection credentials', and Jentic returns the matching Prisma operation with its input schema, including projectId and region, so the agent calls the right endpoint directly.

FAQs

Specific to using Prisma Postgres Management API through Jentic.

What authentication does the Prisma Postgres Management API use?

Per its OpenAPI spec, the Prisma Postgres Management API accepts OAuth2 via the authorization code flow at auth.prisma.io with the workspace:admin and offline_access scopes, or a bearer JWT token such as a workspace service token. POST /v1/auth/github-actions/token is a public endpoint that needs no credential: it exchanges a GitHub Actions OIDC token for a workspace service token. Through Jentic the token is held by your own instance and attached at call time.

Can I restore a database from a backup with the Prisma Postgres Management API?

Yes. GET /v1/databases/{databaseId}/backups lists the backups, and POST /v1/databases/{targetDatabaseId}/restore replaces the target database's data from a backup given in the required source field. The spec marks restore as destructive: it immediately and irreversibly overwrites all data, while connections and credentials are preserved.

What are the rate limits for the Prisma Postgres Management API?

The OpenAPI spec documents a rate limit exceeded response but does not state numeric limits. Check the Prisma documentation at https://www.prisma.io/docs for current limits before scripting bulk provisioning.

Is there a Prisma Postgres MCP server?

You don't need an MCP server to give your agent the Prisma Postgres Management API. Jentic connects it directly from the API Directory: import it, store your token once, and your agent discovers the project, database, and connection operations on demand instead of loading every operation into its context.

How do I create a Prisma Postgres database through Jentic?

Search Jentic for 'create a Postgres database', load postV1Projects, and execute it with a name and region to create a project with a database, or call postV1Databases with a projectId to add one to an existing project. Then create a connection string for the app. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Can I limit what my agent is allowed to do with the Prisma Postgres Management API?

Yes. Write a rule that allows only the reads and the connection-string create under /v1/databases/db_123/, so the agent can inspect that one database, check its backups and usage, and issue a connection string, but cannot restore over it or delete it. Every call it makes is logged for review.

Prisma Postgres Management API

AI ReadinessFoundational (C+)60/100

See full scorecard

Official vendor OpenAPI document · agent-readyStorageDatabaseoauth2, bearer117 EndpointsREST

For Agents

Create Prisma Postgres projects and databases, issue and rotate connection strings, restore from backups, and read usage metrics, plus manage branches, services, and environment variables in a workspace.

Use for: I need a new Postgres database for my side project, Get a connection string for my Prisma Postgres database, Rotate the credentials on my app's database connection, List all backups for my production database

Not supported: Does not run SQL queries, apply schema migrations, or generate Prisma Client code. Use for provisioning and operating Prisma Postgres projects, databases, and connections only.

The Prisma Postgres Management API provisions and operates Prisma Postgres projects, databases, connections, and backups across your workspaces. It creates a project with a Postgres database in a chosen region, issues and rotates connection strings, lists backups and restores a database from one, and reports usage metrics between a startDate and endDate. Beyond the database it manages branches keyed by gitName, services and their deployments, storage buckets and bucket keys, environment variables, source repository links, and workspace service tokens.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A-Signals: 4

94%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

100%

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

14%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: B-Signals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

51%

Response Coverage

Percentage of operations with complete response definitions (success, client error, server error).

100%

Tooling Readiness

Health of API ingestion, bundling, and resolution within Jentic pipelines.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: FSignals: 4

17%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

72%

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

62%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A-Signals: 1

80%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: ASignals: 1

82%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: A-Signals: 1

70%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Prisma Postgres Management API to your agent

Capabilities

Start building with Prisma Postgres Management API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Prisma Postgres Management API

Jentic AI Readiness Score

Prisma Postgres Management API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness