Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Descope 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%2Fdescope.com%2Fdescope" | 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%2Fdescope.com%2Fdescope" | 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 Descope API.
Run passwordless sign-up and sign-in over one-time codes, magic links, and enchanted links
Validate, refresh, and revoke user sessions
Read the current user's details and session history
Administer users, tenants, roles, and permissions in a project
Issue and exchange access keys for machine authentication
GET STARTED
Drive third-party OAuth application authorize and token flows
Sign a user out of one session or all active sessions
Patterns agents use Descope API for, with concrete tasks.
★ Agent-Managed Authentication via Jentic
AI agents drive Descope authentication through Jentic without holding the project token in context. An agent searches by intent, receives the matching operation schema, and runs a passwordless flow or validates a session end to end. Jentic injects the bearer token at execution time, so the agent never sees the secret while it manages sign-in and sessions for a project.
Search Jentic for 'validate a Descope session', load the POST /v1/auth/validate schema, and check the session with Jentic-managed credentials
Passwordless Login Automation
An agent runs an end-to-end passwordless login: it starts a sign-in over a one-time code or magic link, waits for the user to confirm, verifies the token, and receives a session. Descope supports several factors, so the agent can pick the channel that fits the user and complete authentication without a password anywhere in the flow.
Call POST /v1/auth/magiclink/verify to confirm the token, then POST /v1/auth/validate to validate the resulting session
Session Lifecycle Control
An agent keeps a user's session healthy over a long-running task: it validates the session before each sensitive step, refreshes it as it nears expiry, and signs the user out when the task ends. Descope exposes explicit validate, refresh, and sign-out operations, so the agent controls the full session lifecycle rather than guessing at token state.
Call POST /v1/auth/refresh to extend a session, then POST /v1/auth/logout to sign the user out when done
240 endpoints — the descope api gives ai agents programmatic control over authentication and identity for a project.
METHOD
PATH
DESCRIPTION
/v1/auth/enchantedlink/signin/email
Start a passwordless enchanted-link sign-in by email
/v1/auth/magiclink/verify
Verify a magic link token and create a session
/v1/auth/validate
Validate an active session
/v1/auth/refresh
Refresh an expiring session
/v1/auth/me
Read the current user's details
/v1/auth/logout
Sign the current user out of their session
/v1/auth/enchantedlink/signin/email
Start a passwordless enchanted-link sign-in by email
/v1/auth/magiclink/verify
Verify a magic link token and create a session
/v1/auth/validate
Validate an active session
/v1/auth/refresh
Refresh an expiring session
/v1/auth/me
Read the current user's details
/v1/auth/logout
Sign the current user out of their session
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Descope API by hand means managing a project bearer token for each credential type, sequencing sign-up, verify, and validate calls, and handling refresh and revoke yourself. Through Jentic you install once, import the Descope API from the API Directory, store the token, and your agent calls it.
Permission scoping
You choose which Descope operations your agent may call, so a rule can allow session validation and user lookups while withholding user deletion, role edits, or access-key issuance. Scoping is by operation, so state-changing calls stay out unless you grant them.
Credential isolation
Your Descope bearer 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 'validate a session' or 'refresh a token', and Jentic returns the matching Descope 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 Descope API through Jentic.
What authentication does the Descope API use?
The Descope API authenticates requests with a bearer token sent in the Authorization header, per its OpenAPI spec. Depending on the operation the token is a project ID, a JWT, a session JWT, an access key, or a management key. 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 passwordless sign-in with the Descope API?
Yes. Start a flow such as POST /v1/auth/enchantedlink/signin/email, confirm the token with POST /v1/auth/magiclink/verify, then validate the resulting session with POST /v1/auth/validate.
What are the rate limits for the Descope API?
The OpenAPI spec does not specify rate limits; check the Descope documentation for current limits. Through Jentic, requests run from your own instance, so you control the pacing of the agent's calls.
How do I validate a session with the Descope API through Jentic?
Search Jentic for 'validate a Descope session', load the returned POST /v1/auth/validate operation with its input schema, and your agent checks the session with credentials injected at call time. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Is there a Descope MCP server?
You don't need an MCP server to give your agent the Descope API. Jentic connects it directly from the API Directory: import it, store your token, and your agent calls it, discovering operations on demand instead of loading a separate server's tool definitions into its context.
Can I limit what my agent is allowed to do with the Descope API?
Yes. You choose which Descope operations your agent may call, so you can allow read-only checks like validating a session or reading user details while withholding user deletion or role changes. Scoping is by operation, so the agent invokes only the endpoints you approve.
For Agents
Run passwordless sign-in, session, and user-management flows for a Descope project. Authenticates with a project bearer token.
Use for: I want to start a passwordless sign-in with a one-time code, Verify a magic link token and create a session, Validate an active session token, Refresh an expiring session
Not supported: Does not host your application UI or store business data. Use for authentication, session, and identity management only.
The Descope API gives AI agents programmatic control over authentication and identity for a project. Agents run passwordless sign-up and sign-in flows over one-time codes, magic links, enchanted links, and OAuth, then validate, refresh, and revoke the resulting sessions. Beyond end-user auth, agents administer users, tenants, roles, permissions, and access keys, and drive third-party OAuth application flows. Requests present a bearer token scoped to the project.
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>