Install Jentic One Beta

Connect the Jid API to your agent

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

Resolve a business name or identifier (FEI, LEI, CIK, DUNS, NPI, EIN, UEI, USDOT, state numbers) to candidate Jid files with GET /v1/search

Verify a business with GET /v1/entities/{id}/verify and, with an activity, jurisdiction, or amount, get a decision of proceed, review, stop, or insufficient_data plus a signed receipt

Read the full business file with location, owner statements, possible matches, and the last 50 change events via GET /v1/entities/{id}

Get an engage-or-not answer with risk, reasons, and mitigations from a domain, url, email, phone, or company_name with POST /v1/screen

GET STARTED

Start building with Jid API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Jid API for, with concrete tasks.

★ Pre-payment counterparty checks through Jentic

An agent about to pay, book, or sign with a business should check it first. Through Jentic it finds the Jid operations by intent: GET /v1/search turns the name or identifier into a file id, and GET /v1/entities/{id}/verify with an activity, jurisdiction, and amount returns proceed, review, stop, or insufficient_data with reasons and a signed receipt. The agent acts only on proceed, and the jid_live_ key is injected at call time and never sits in its context.

Call GET /v1/search with q set to the supplier's EIN, then GET /v1/entities/{id}/verify with activity 'general_commerce', jurisdiction 'US-CO', amount 20000, and currency 'USD', and continue only if decision is 'proceed'

Phishing and invoice-fraud screening

Payment-redirect scams arrive as convincing emails. POST /v1/email-check reads the receiving server's Authentication-Results, Received-SPF, DKIM alignment with From, Reply-To versus From, and whether the From domain imitates a known company's registered domain, returning checks and a read of engage, verify_first, or do_not_engage. POST /v1/screen gives a deterministic engage-or-not answer from the sender's domain or email with reasons and sources.

Call POST /v1/email-check with headers set to the raw message headers, and if the read is 'do_not_engage' or 'verify_first', flag the email instead of paying

Inbound lead qualification

Sales teams waste time on junk form submissions. POST /v1/qualify checks the domain's MX, SPF, DMARC, and registration date, matches it to a Jid file, and returns legitimacy, capacity, and consistency scores from 0 to 100 with reasons, a recommendation, and questions to ask. POST /v1/outcomes records what you decided, such as legit or spam, which tunes the published rules.

Call POST /v1/qualify with email and company_name from the form, then after the call with the lead record POST /v1/outcomes with result_id and outcome 'legit' or 'spam'

Ongoing vendor monitoring

A vendor that was licensed at onboarding may not stay that way. POST /v1/monitors watches a Jid file by entity_id and delivers each change with old and new values to a webhook_url or email; GET /v1/monitors lists monitors and DELETE /v1/monitors removes one by id.

Call POST /v1/monitors with entity_id set to the vendor's Jid file id and webhook_url set to your alerts endpoint

Key Endpoints

15 endpoints — the jid api checks the business an agent is about to pay, sign with, book, hire, or buy from: whether it is real, active, licensed for the activity, and not sanctioned, with every fact cited to the registry that issued it.

METHOD

PATH

DESCRIPTION

GET

/v1/search

Resolve a name or registry number to candidate files

GET

/v1/entities/{id}/verify

Verify a business and get a decision

GET

/v1/entities/{id}

Get the full business file

POST

/v1/screen

Engage-or-not screen

POST

/v1/email-check

Check email headers

POST

/v1/qualify

Qualify a lead or counterparty

GET

/v1/receipts/{receipt_id}

Retrieve a signed receipt

POST

/v1/monitors

Watch a business file

GET

/v1/search

Resolve a name or registry number to candidate files

GET

/v1/entities/{id}/verify

Verify a business and get a decision

GET

/v1/entities/{id}

Get the full business file

POST

/v1/screen

Engage-or-not screen

POST

/v1/email-check

Check email headers

POST

/v1/qualify

Qualify a lead or counterparty

GET

/v1/receipts/{receipt_id}

Retrieve a signed receipt

POST

/v1/monitors

Watch a business file

Why Jentic?

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

Setup

Wiring Jid by hand means handling its optional jid_live_ bearer key, knowing which operations need it, and chaining search into verify with the right activity and jurisdiction codes. Through Jentic you install once, import the Jid API from the API Directory, store the key once, and your agent calls it.

Permission scoping

Jid puts the business file id in the URL path (/v1/entities/{id}/verify), so a rule can pin your agent to checking one named business. You choose the operations it may call, so monitor creation or deletion and outcome reporting are not included unless you add them.

Credential isolation

Your Jid 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 'verify a business before paying' or 'is this email really from them', and Jentic returns the matching Jid operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Jid API through Jentic.

Is there a Jid MCP server?

You don't need an MCP server to give your agent the Jid API. Jentic connects it directly from the API Directory: import it, store your Jid key once, and your agent calls it. Operations are discovered on demand, so no extra tool definitions sit in the agent's context.

What authentication does the Jid API use?

Per its OpenAPI spec, the Jid API takes a jid_live_ key sent as a bearer token in the Authorization header. The key is optional on search, verify, screen, and email-check, which run on a per-IP free tier without one, and required on POST /v1/qualify, GET /v1/results, and the monitors operations. GET /v1/signal is open and called from the visitor's browser. Through Jentic, the key is stored encrypted by your own Jentic One instance and injected at call time.

What are the rate limits for the Jid API?

Per the OpenAPI spec, calls without a key are limited to 10 requests a minute and 100 a day per IP. A free key, with no card, includes 1,000 checks a month, and POST /v1/qualify counts as 2 checks. See https://jid.com/pricing for paid tiers.

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

Yes. For example, write a rule that allows only GET /v1/search and GET /v1/entities/{id}/verify. Your agent can then look up and verify businesses but cannot create or delete monitors or record outcomes, and every call it makes is logged.

Is a Jid decision legal advice?

No. Decisions apply Jid's published decision rules and are not legal advice, and the data is business information only, not a consumer report and not for FCRA purposes. Act only on proceed: requirements Jid cannot check are treated as unknown and lead to review.

How do I verify a business through Jentic?

Search Jentic for 'verify a business before paying', load the verifyBusiness operation, and call GET /v1/entities/{id}/verify with the file id from GET /v1/search plus an activity and jurisdiction to get a decision and signed receipt. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Can someone else check a Jid receipt?

Yes. GET /v1/receipts/{receipt_id} is free and readable by anyone holding the receipt id, so it can be shown to an auditor or counterparty, who can verify signature.sig against the key published at /.well-known/jid-keys.json.

Jid API

AI ReadinessAI-Aware (B-)62/100

See full scorecard

Official vendor OpenAPI document · agent-readyIdentity AuthIdentity Verificationbearer15 EndpointsREST

For Agents

Verify a business against official registries before acting, get a proceed, review, or stop decision with a signed receipt, screen domains and emails for engage-or-not answers, qualify leads, and monitor business files for changes.

Use for: Check whether this freight broker is licensed before I book a load, Find the Jid file for a company by its EIN, Should I engage with the sender of this invoice email?, Verify a supplier before paying a 20,000 USD invoice

Not supported: Does not verify individual consumers, produce credit or FCRA consumer reports, or give legal advice. Use for registry-cited business verification and engage-or-not screening only.

The Jid API checks the business an agent is about to pay, sign with, book, hire, or buy from: whether it is real, active, licensed for the activity, and not sanctioned, with every fact cited to the registry that issued it. It resolves a name or identifier such as an LEI, EIN, DUNS, NPI, or USDOT number to a Jid file, verifies that file and, given an activity like haul_freight or sell_alcohol plus a jurisdiction or amount, returns a proceed, review, stop, or insufficient_data decision with an Ed25519-signed receipt. A screen operation gives a deterministic engage-or-not answer from a domain, email, phone, or company name, an email check reads raw headers for SPF, DKIM, DMARC, and lookalike domains, and keyed accounts can qualify inbound leads and monitor files for changes. It provides business information only, not consumer reports.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A-Signals: 4

98%

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).

10%

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.

48%

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: D-Signals: 4

27%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

87%

OperationId Quality

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

57%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A+Signals: 1

94%

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: A-Signals: 1

78%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Jid API to your agent

Capabilities

Start building with Jid API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Jid API

Jentic AI Readiness Score

Jid 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