Install Jentic One Beta

Connect the CorroborateMe API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the CorroborateMe 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%2Fcorroborateme.com%2Fcorroborateme" | 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%2Fcorroborateme.com%2Fcorroborateme" | 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 CorroborateMe API.

Create a one-time login-link session and poll its status until the human completes it

Verify a human through OTP, password, or passkey flows on a login-link

Mint and revoke a company's API keys

List login-link end-users and GDPR-erase a specific user

GET STARTED

Start building with CorroborateMe API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use CorroborateMe API for, with concrete tasks.

★ Human Verification for Agents

An agent that needs a real person to confirm an action creates a one-time login-link session and polls it until the human signs in through OTP, password, or passkey. CorroborateMe bridges the interactive login and returns the completed session, so the agent gets a verified end user without implementing the login UI itself.

Create a session with POST /api/login-links, then poll GET /api/login-links/{id} until the login completes

Programmatic Key and OIDC Management

A company agent mints scoped API keys, revokes keys that are no longer needed, and registers OIDC relying-party clients for single sign-on. CorroborateMe returns key metadata without ever re-exposing secrets and exposes OIDC discovery and JWKS, so the agent can wire SSO and rotate credentials under one company.

Mint a key with POST /api/companies/{id}/keys, then register an SSO client with POST /api/oidc/clients

AI Agent Integration via Jentic

An AI agent reaches CorroborateMe through Jentic without handling the bearer token itself. It searches by intent, receives the matching operation and its input schema, and executes the call with the credential injected at run time. This lets an agent request a human verification mid-task without the builder wiring login-link polling by hand.

Search Jentic for 'create a login-link for a user', load the POST /api/login-links schema, and execute it with Jentic-managed credentials

Key Endpoints

52 endpoints — the corroborateme api proves end users to agents and apps through login-links, api keys, and oidc.

METHOD

PATH

DESCRIPTION

POST

/api/login-links

Create a one-time human login-link session

GET

/api/login-links/{id}

Poll a login-link status

POST

/api/companies/{id}/keys

Mint a company API key

POST

/api/companies/{id}/keys/{keyId}/revoke

Revoke a company API key

POST

/api/oidc/clients

GET

/api/end-users

List login-link end-users

GET

/api/budget

Read remaining quotas for a company

POST

/api/login-links

Create a one-time human login-link session

GET

/api/login-links/{id}

Poll a login-link status

POST

/api/companies/{id}/keys

Mint a company API key

POST

/api/companies/{id}/keys/{keyId}/revoke

Revoke a company API key

POST

/api/oidc/clients

GET

/api/end-users

List login-link end-users

GET

/api/budget

Read remaining quotas for a company

Why Jentic?

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

Setup

Wiring CorroborateMe by hand means managing a bearer token that can take several forms, polling login-link sessions while a human completes OTP or passkey steps, and tracking which endpoints are public. Through Jentic you install once, import CorroborateMe from the API Directory, store the credential once, and your agent calls it.

Permission scoping

CorroborateMe puts the company id in the URL path (/api/companies/{id}/...), so a rule can pin your agent to one company: it can create login-links and read key metadata for that company and nothing else. You choose which operations it may call, so destructive ones like key revocation or GDPR end-user erase are not included unless you add them.

Credential isolation

Your CorroborateMe credential 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 login-link' or 'mint an API key', and Jentic returns the matching CorroborateMe operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using CorroborateMe API through Jentic.

What authentication does the CorroborateMe API use?

The CorroborateMe API authenticates with a bearer token in the Authorization header, per its OpenAPI spec. That token can be a console session JWT, a company end-user JWT, a bootstrap JWT, or a company API key. Health, public config, and the interactive login-link steps are open and need no credential. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at execution time, so it never reaches the agent.

Can I verify a human with the CorroborateMe API?

Yes. You create a one-time login-link session, then poll its status while the person completes an OTP, password, or passkey login, and read the completed session when they finish. The login-link bridges the interactive login so an agent gets a verified end user without building the login UI.

What are the rate limits for the CorroborateMe API?

The OpenAPI spec does not publish specific rate-limit numbers; check https://corroborateme.com/swagger for current details. The budget endpoint reports a company's remaining verification quotas, so an agent can confirm it has headroom before minting keys or issuing login-links.

Is there a CorroborateMe MCP server?

You don't need an MCP server to give your agent CorroborateMe. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls the login-link and key operations. Nothing extra is loaded into the agent's context until an operation is actually invoked.

Can I limit what my agent is allowed to do with the CorroborateMe API?

Yes. CorroborateMe puts the company id in the URL path, so write a rule that pins your agent to one company and allows only the login-link and key-read operations, leaving key revocation and GDPR erase out of reach. Every call runs through your own Jentic One instance and is logged for you to review.

How do I create a login-link with the CorroborateMe API through Jentic?

Search Jentic for 'create a login-link for a user', and it returns the CorroborateMe login-link operation with its input schema. Load the schema and execute POST /api/login-links, then poll GET /api/login-links/{id}, with the credential injected at run time. To run it on your own infrastructure, install Jentic One from its GitHub repo.

CorroborateMe API

AI ReadinessFoundational (D)45/100

See full scorecard

Official vendor OpenAPI document · agent-readyIdentity AuthAuthenticationbearer52 EndpointsREST

For Agents

Create one-time login-link sessions to verify a human, mint and revoke company API keys, and register OIDC clients. Authenticated with a bearer token that may be a console JWT, end-user JWT, bootstrap JWT, or API key; several endpoints are public.

Use for: Create a one-time login-link to verify a human, Poll a login-link until the user has signed in, Mint a new API key for a company, Register an OIDC client for single sign-on

Not supported: Does not handle payment processing, email delivery, or analytics. Use for verifying end users through login-links, API keys, and OIDC only.

The CorroborateMe API proves end users to agents and apps through login-links, API keys, and OIDC. It mints one-time login-link sessions that bridge an interactive human login, supports OTP, password, and passkey flows on those sessions, and registers OIDC relying-party clients with discovery and JWKS endpoints. Companies manage their own API keys, console members, OIDC clients, and login-link end-users, including GDPR erase, and can read remaining quotas before issuing more verifications.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A+Signals: 4

96%

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).

75%

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: C+Signals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

31%

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

31%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

OperationId Quality

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

53%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A+Signals: 1

93%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: B-Signals: 1

60%

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: BSignals: 1

64%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the CorroborateMe API to your agent

Capabilities

Start building with CorroborateMe API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

CorroborateMe API

Jentic AI Readiness Score

CorroborateMe 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