Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the OVHcloud 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%2Fovh.com%2Fovh" | 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%2Fovh.com%2Fovh" | 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 OVHcloud API.
Provision and manage public cloud instances, volumes, and private networks
List and reboot dedicated servers and track their provisioning tasks
Start, stop, and reinstall VPS instances and manage their snapshots
Manage DNS zones and records, including DNSSEC and reverse DNS
Configure IP firewall rules, reverse DNS, and DDoS mitigation
GET STARTED
Read account billing, orders, and SSL certificate status
Patterns agents use OVHcloud API for, with concrete tasks.
★ AI Agent Infrastructure Operations
An AI agent running ops tasks can create instances, manage DNS, and check billing across OVHcloud through Jentic. The agent searches for the operation it needs, supplies the service name and parameters, and runs the call, without the developer hand-building the application key header or paging through the OVHcloud reference docs.
Call POST /cloud/project/{serviceName}/instance to create a new instance in a project
DNS Automation
DevOps pipelines keep DNS in sync with deployments. OVHcloud exposes zone and record operations, so an agent can add an A record for a new service, refresh the zone, and confirm the change through the zone status operation.
Call POST /domain/zone/{zoneName}/record to add a DNS record, then POST /domain/zone/{zoneName}/refresh
Server Fleet Management
Teams managing bare-metal and virtual fleets reboot, reinstall, and inspect machines at scale. OVHcloud lists dedicated servers and VPS instances and exposes reboot, reinstall, and task-tracking operations, so an agent can act on a host and watch the resulting task to completion.
Call GET /dedicated/server to list servers, then POST /dedicated/server/{serviceName}/reboot to reboot one
102 endpoints — the ovhcloud api manages public cloud, dedicated servers, vps, domains, dns, ip addresses, ssl certificates, and billing across ovhcloud regions.
METHOD
PATH
DESCRIPTION
/cloud/project
List public cloud projects
/cloud/project/{serviceName}/instance
Create a cloud instance
/domain/zone/{zoneName}/record
List DNS records in a zone
/domain/zone/{zoneName}/record
Create a DNS record
/dedicated/server
List dedicated servers
/vps
List VPS instances
/ip
List IP addresses
/me/bill
List account bills
/cloud/project
List public cloud projects
/cloud/project/{serviceName}/instance
Create a cloud instance
/domain/zone/{zoneName}/record
List DNS records in a zone
/domain/zone/{zoneName}/record
Create a DNS record
/dedicated/server
List dedicated servers
/vps
List VPS instances
/ip
List IP addresses
/me/bill
List account bills
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the OVHcloud API by hand means signing requests with your application key, choosing the right regional host for your account, and tracking asynchronous server tasks yourself. Through Jentic you install once, import OVHcloud from the API Directory, store the key once, and your agent calls it.
Permission scoping
OVHcloud puts the service name in the URL path, so a rule can keep your agent on the operations and services you pick, such as reading cloud projects and DNS records. You choose the operation set, so destructive operations like deleting an instance or terminating a dedicated server are not included unless you add them.
Credential isolation
Your OVHcloud application key 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 'create a cloud instance' or 'add a DNS record', and Jentic returns the matching OVHcloud 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 OVHcloud API through Jentic.
What authentication does the OVHcloud API use?
The OVHcloud API authenticates with an application key sent in the `X-Ovh-Application` header, per its OpenAPI spec; most operations require it, while the credential-request and server-time endpoints are open. Through Jentic the key 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 create a cloud instance with the OVHcloud API?
Yes. The cloud instance operation creates an instance in a project from a chosen flavor and image, and companion operations list flavors, images, and the resulting instance so you can confirm it came up. Volumes and private networks are managed through their own operations in the same project.
What are the rate limits for the OVHcloud API?
The OpenAPI spec does not specify rate limits; OVHcloud applies limits per application and account. Current limits are documented in the vendor documentation at https://api.ovh.com/.
How do I manage DNS with the OVHcloud API through Jentic?
Install Jentic One with `curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh`, import OVHcloud from the API Directory, and store your application key once. Your agent then searches for an intent such as 'add a DNS record', and Jentic returns the matching operation with its input schema. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Is there an OVHcloud MCP server?
You do not need an MCP server to give your agent the OVHcloud API. Jentic connects it directly from the API Directory: import the API, store your key once, and your agent calls the cloud, DNS, and billing operations on demand, which keeps your agent's context free of an extra server's tool definitions.
Can I limit what my agent is allowed to do with the OVHcloud API?
Yes. OVHcloud is a large write-capable API, so you can allow your agent just the operations a task needs, such as listing servers and reading bills, and leave out destructive ones like deleting an instance or terminating a dedicated server. Because you run Jentic One yourself, the agent operates only within the operation set you grant, and every call is logged.
For Agents
Provision cloud instances, manage dedicated servers and VPS, edit DNS and IP configuration, and read billing across OVHcloud. Authenticates with an application key.
Use for: Create a new cloud instance in a project, List all my dedicated servers, Reboot a VPS by its service name, Add a DNS record to a zone
Not supported: Does not handle application code deployment, container orchestration, or managed databases. Use for OVHcloud infrastructure, DNS, and account management only.
The OVHcloud API manages public cloud, dedicated servers, VPS, domains, DNS, IP addresses, SSL certificates, and billing across OVHcloud regions. It provisions and controls cloud instances, volumes, and private networks, reboots and reinstalls dedicated servers and VPS, and edits DNS zones and records including DNSSEC and reverse DNS. Account operations expose bills, orders, debt, and SSL certificate status so infrastructure and spend can be driven together.
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>