Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the env0 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%2Fenv0.com%2Fenv0" | 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%2Fenv0.com%2Fenv0" | 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 env0 API.
Create an environment and trigger a deployment or a destroy run
List the deployments recorded against an environment
Manage blueprint templates that environments are provisioned from
Organise environments into projects and manage project membership
Set and update configuration variables for deployments
GET STARTED
Administer teams and create or list API keys
Patterns agents use env0 API for, with concrete tasks.
★ Agent-Driven Environment Deployment
An AI agent connected through Jentic provisions infrastructure by creating an environment from a blueprint, setting the configuration variables it needs, and triggering a deployment. Because env0 models create, deploy, and destroy as distinct operations, the agent runs a controlled deployment flow and can tear the environment down with an explicit destroy call when it is done.
Create an environment from a blueprint, set one configuration variable, and trigger a deployment
Self-Service Project Setup
A platform team gives developers self-service infrastructure by provisioning projects and the templates behind them. The env0 API creates projects, registers blueprint templates, and manages team access, so an agent stands up a new project with its approved templates and the right teams attached.
Create a project, attach a blueprint template to it, and grant a team access to the project
Deployment Governance and Teardown
An operations workflow controls spend by listing deployments and destroying environments that are no longer needed. The API returns the deployments for an environment and exposes an explicit destroy operation, so an agent reconciles live environments against policy and tears down the ones that should not persist.
List deployments for an environment and, if it is idle, trigger a destroy run
29 endpoints — the env0 api drives infrastructure-as-code deployments on the env0 governance platform.
METHOD
PATH
DESCRIPTION
/environments
List environments
/environments
Create an environment
/environments/{id}/deployments
Deploy an environment
/environments/{id}/destroy
Destroy an environment
/projects
List projects
/projects
Create a project
/blueprints
List blueprint templates
/configuration
List configuration variables
/environments
List environments
/environments
Create an environment
/environments/{id}/deployments
Deploy an environment
/environments/{id}/destroy
Destroy an environment
/projects
List projects
/projects
Create a project
/blueprints
List blueprint templates
/configuration
List configuration variables
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the env0 API by hand means encoding the API Key ID and Secret for HTTP Basic auth and sequencing create, deploy, and destroy calls yourself. Through Jentic you install once, import the env0 API from the API Directory, store the key pair once, and your agent calls the operations.
Permission scoping
env0 puts the environment id in the URL path, so a rule can scope your agent to the operations on one environment. You choose the operations it may call, so destructive ones like destroying or deleting an environment are not included unless you add them.
Credential isolation
Your env0 API Key ID and Secret are held by your own Jentic One instance, encrypted, and injected into the Basic auth header at execution time. They never enter the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'deploy an environment' or 'list deployments', and Jentic returns the matching env0 operation with its input schema so the agent runs the right step in the deployment flow.
Alternatives and complements available in the Jentic catalogue.
Specific to using env0 API through Jentic.
What authentication does the env0 API use?
The env0 API uses HTTP Basic authentication, per its OpenAPI spec: you send the API Key ID as the username and the API Key Secret as the password. Through Jentic the credential is held by your own Jentic One instance and attached at execution time, so it never appears in your agent's prompt or logs.
Can I deploy and destroy environments with the env0 API?
Yes. The API creates an environment, triggers a deployment, lists the deployments recorded against it, and destroys it with an explicit operation. Your agent can run a controlled create, deploy, and teardown flow for an environment.
What are the rate limits for the env0 API?
The OpenAPI spec does not specify rate limits. Check the env0 documentation at https://docs.env0.com for the current limits before running frequent deployment operations.
Is there an env0 MCP server?
You do not need an MCP server to give your agent the env0 API. Jentic connects it directly from the API Directory: import it, store your API Key ID and Secret once, and your agent discovers the environment and project operations it needs 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 env0 API?
Yes. env0 puts the environment id in the URL path, so a rule can scope your agent to the operations on one environment, and you choose the operations it may call. Destructive ones like destroying or deleting an environment stay out unless you add them, and every call it makes is logged.
How do I deploy an env0 environment 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 env0 API from the Jentic directory and search by intent such as 'deploy an infrastructure environment'. 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
Deploy and destroy infrastructure-as-code environments on env0, manage blueprints and projects, set configuration variables, and administer teams and API keys.
Use for: Deploy an infrastructure environment on env0, Create a new project to group my environments, List all deployments for a given environment, Update a configuration variable before a deployment
Not supported: Does not provision cloud resources directly, run application CI builds, or store Terraform state files. Use for env0 infrastructure-as-code deployment and governance only.
The env0 API drives infrastructure-as-code deployments on the env0 governance platform. Your agent creates environments, deploys and destroys them, and lists their deployments, while managing the templates (called blueprints) that environments are provisioned from. It also organises work into projects, sets configuration variables, and administers organizations, teams, and API keys so an automation can run a full self-service deployment flow.
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>